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
     :-
    -0.07
    _REQ
    -0.06
     boob
    -0.06
    onis
    -0.06
    +
    -0.06
    errick
    -0.06
    达到
    -0.06
    abile
    -0.06
    íše
    -0.06
    ไล
    -0.06
    POSITIVE LOGITS
     *=
    0.27
    *=
    0.14
     /=
    0.13
     //=
    0.08
     уд
    0.08
    //=
    0.08
    /=
    0.07
     <<=
    0.07
     ^=
    0.07
     رئیس
    0.07
    Act Density 0.001%

    No Known Activations