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

    Neuronpedia

    INDEX
    Explanations

    specific names and terms, particularly those related to individuals or places

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

    Capitalized word starts

    np_acts-logits-general · gemini-2.0-flash

    names starting with two letters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    h
    -0.67
    hua
    -0.60
    y
    -0.60
    in
    -0.57
    ua
    -0.55
    u
    -0.55
     esternos
    -0.55
    sias
    -0.53
    StoryboardSegue
    -0.53
    ya
    -0.53
    POSITIVE LOGITS
    red
    0.50
    shampoo
    0.45
     doInBackground
    0.42
    fault
    0.42
    feelings
    0.42
    fanart
    0.42
    fei
    0.42
    ft
    0.41
    faults
    0.41
    fee
    0.41
    Act Density 0.340%

    No Known Activations