Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    sections discussing evaluations, advantages, and disadvantages of items or procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text after "Weaknesses," "CONS," or "Disadvantages"

    np_acts-logits-general · gemini-2.0-flash

    downsides or negative aspects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    posedge
    -0.62
    +#+
    -0.58
    HtmlAttribute
    -0.53
    principalTable
    -0.53
    abetes
    -0.52
     ddelwed
    -0.49
     Normdatei
    -0.49
     onPostExecute
    -0.48
     tiguan
    -0.47
     ſei
    -0.47
    POSITIVE LOGITS
    SequentialGroup
    0.55
    StructEnd
    0.40
    Dislikes
    0.38
    匿名使用者
    0.36
    estacks
    0.36
     posses
    0.34
    ️
    0.34
     Happ
    0.34
    middot
    0.33
     behar
    0.33
    Act Density 0.089%

    No Known Activations