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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     liền
    -0.07
     inevitable
    -0.07
     enhanced
    -0.07
     developer
    -0.07
     modelo
    -0.07
     erotica
    -0.07
     Ps
    -0.07
     tighter
    -0.07
    啡
    -0.06
    ?.
    -0.06
    POSITIVE LOGITS
    .RowCount
    0.09
    serve
    0.07
     Rupert
    0.07
    LOGY
    0.07
    ্
    0.07
     Wroc
    0.06
     aup
    0.06
     atrav
    0.06
    pop
    0.06
    뿌
    0.06
    Act Density 0.083%

    No Known Activations