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

    Neuronpedia

    INDEX
    Explanations

    .log

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    与
    -0.08
    Forecast
    -0.07
    _spot
    -0.07
     telegram
    -0.06
     правда
    -0.06
    studio
    -0.06
    aden
    -0.06
    Cursor
    -0.06
    출
    -0.06
    _CLIENT
    -0.06
    POSITIVE LOGITS
     advancement
    0.06
     blok
    0.06
    MT
    0.06
    '=>'
    0.06
     Divide
    0.06
     दस
    0.06
     controversial
    0.06
    ájem
    0.06
    BUM
    0.06
     widespread
    0.06
    Act Density 0.008%

    No Known Activations