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

    Neuronpedia

    INDEX
    Explanations

    terms associated with strength or robustness

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

    "strong"

    np_acts-logits-general · gemini-2.0-flash

    the word strong

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MLLoader
    -0.70
     resourceCulture
    -0.69
     виправивши
    -0.63
     مرئيه
    -0.63
    StoryboardSegue
    -0.60
    yntaxException
    -0.58
     متعلقه
    -0.57
     Tripura
    -0.56
     hablamos
    -0.56
     felizes
    -0.55
    POSITIVE LOGITS
    STRONG
    1.28
     Strong
    1.23
    Strong
    1.19
    strong
    1.17
     strong
    1.16
     STRONG
    1.14
     Weak
    1.09
     weak
    1.07
     stronger
    1.06
     strongest
    1.04
    Act Density 0.107%

    No Known Activations