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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UPDATE
    -0.06
     '@
    -0.06
     straps
    -0.06
     Sith
    -0.06
     pec
    -0.06
     Belediye
    -0.06
     Corrections
    -0.06
    oun
    -0.06
    �
    -0.06
     Ben
    -0.06
    POSITIVE LOGITS
     حم
    0.08
    .В
    0.08
    --)
    0.06
     insecurity
    0.06
    /GPL
    0.06
    Tai
    0.06
    Different
    0.06
     sulfate
    0.06
     oyuncu
    0.06
    Server
    0.06
    Act Density 0.095%

    No Known Activations