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

    Neuronpedia

    INDEX
    Explanations

    Creation or formation processes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.06
     кат
    -0.06
    juries
    -0.06
    Career
    -0.06
    /classes
    -0.06
    loud
    -0.06
    alous
    -0.06
    .First
    -0.06
    jured
    -0.06
    cluding
    -0.06
    POSITIVE LOGITS
     نمی
    0.07
    _BACKEND
    0.06
    alfa
    0.06
    _grp
    0.06
    _toolbar
    0.06
    减
    0.06
     groupe
    0.06
     american
    0.06
    童
    0.06
     StringWriter
    0.06
    Act Density 0.178%

    No Known Activations