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

    Neuronpedia

    INDEX
    Explanations

    25

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     attacks
    -0.07
    яд
    -0.07
     �
    -0.06
    _restore
    -0.06
     wiped
    -0.06
    	swap
    -0.06
    (IB
    -0.06
    ière
    -0.06
    θή
    -0.06
     echoed
    -0.06
    POSITIVE LOGITS
    gram
    0.08
    .--
    0.07
     Caller
    0.06
     Carnegie
    0.06
    -res
    0.06
    _guid
    0.06
    ')}}</
    0.06
     kcal
    0.06
    untas
    0.06
     entering
    0.06
    Act Density 0.000%

    No Known Activations