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

    Neuronpedia

    INDEX
    Explanations

    went

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nintendo
    -0.07
     HTTPS
    -0.06
     Stadt
    -0.06
    .index
    -0.06
     Vatican
    -0.06
     agendas
    -0.06
     розви
    -0.06
    ецт
    -0.06
    _train
    -0.06
     작업
    -0.06
    POSITIVE LOGITS
     whose
    0.07
    ResponseBody
    0.06
     znač
    0.06
    стри
    0.06
    猛
    0.06
    /pass
    0.06
     बद
    0.06
     Myth
    0.06
    digits
    0.06
     INFO
    0.06
    Act Density 0.024%

    No Known Activations