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

    Neuronpedia

    INDEX
    Explanations

    pond

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     timber
    -0.06
    RU
    -0.06
    :]↵
    -0.06
    ...)↵
    -0.06
     demonstrates
    -0.06
     Square
    -0.06
    "]↵
    -0.06
     precipitation
    -0.06
     Either
    -0.06
     clothing
    -0.06
    POSITIVE LOGITS
    okableCall
    0.07
    pa
    0.07
     Aaron
    0.07
    üc
    0.07
    _SSL
    0.07
    .Alpha
    0.06
    보험
    0.06
    _rec
    0.06
    戲
    0.06
    參
    0.06
    Act Density 0.008%

    No Known Activations