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

    Neuronpedia

    INDEX
    Explanations

    can be, exist, represent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     penile
    0.83
    atschapp
    0.73
    kadot
    0.73
    polyfill
    0.73
    0.72
     वाजिब
    0.72
    ܕ
    0.72
     etcétera
    0.71
    <unused1099>
    0.71
    ত্রের
    0.71
    POSITIVE LOGITS
     aucun
    0.67
     handles
    0.66
     likely
    0.63
     handle
    0.63
    場合の
    0.63
     vice
    0.62
    aft
    0.62
     rép
    0.62
    場合
    0.62
     Cmd
    0.62
    Act Density 0.005%

    No Known Activations