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

    Neuronpedia

    INDEX
    Explanations

    power

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    축
    -0.06
     Pou
    -0.06
     فناوری
    -0.06
     sauna
    -0.06
    186
    -0.06
     Butler
    -0.06
     repar
    -0.06
    弗
    -0.06
    electron
    -0.06
     Narc
    -0.06
    POSITIVE LOGITS
     tricks
    0.07
     PropelException
    0.06
    gne
    0.06
     goals
    0.06
     ₹
    0.06
     ################################################################
    0.06
    шается
    0.06
     HinderedRotor
    0.06
    -trade
    0.06
    ım
    0.06
    Act Density 0.336%

    No Known Activations