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

    Neuronpedia

    INDEX
    Explanations

    conjunctions, punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fool
    -0.07
    怎么
    -0.06
    願
    -0.06
    .calc
    -0.06
     Ter
    -0.06
     lifecycle
    -0.06
     вместе
    -0.06
    _deps
    -0.06
     Goat
    -0.06
    /+
    -0.06
    POSITIVE LOGITS
     vaše
    0.07
    σμ
    0.07
    Draft
    0.07
     yaptık
    0.06
    [iVar
    0.06
    lov
    0.06
    Gtk
    0.06
    _wrapper
    0.06
    láv
    0.06
    .rotate
    0.06
    Act Density 0.042%

    No Known Activations