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

    Neuronpedia

    INDEX
    Explanations

    comput

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vál
    -0.08
    Placeholder
    -0.07
     annotate
    -0.07
    (chat
    -0.07
    initialize
    -0.06
    continue
    -0.06
     ku
    -0.06
     lah
    -0.06
     Decoration
    -0.06
     Soon
    -0.06
    POSITIVE LOGITS
     Gravity
    0.07
    อนท
    0.07
    运
    0.07
    .SizeMode
    0.07
     gravity
    0.06
    nutrition
    0.06
    quip
    0.06
     Dough
    0.06
    轉
    0.06
    antas
    0.06
    Act Density 0.014%

    No Known Activations