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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	not
    -0.07
     fury
    -0.07
     cotton
    -0.07
     seulement
    -0.07
     Suppress
    -0.06
    That
    -0.06
    检
    -0.06
    CGPoint
    -0.06
     بالأ
    -0.06
    _CAPACITY
    -0.06
    POSITIVE LOGITS
     bere
    0.06
    (itemView
    0.06
    альну
    0.06
    [N
    0.06
    overnment
    0.06
     bs
    0.06
    атков
    0.06
    ологичес
    0.06
    .tie
    0.06
    iben
    0.06
    Act Density 0.009%

    No Known Activations