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

    Neuronpedia

    INDEX
    Explanations

    sports awards

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    åįıåķĨ
    -0.28
    å¼
    -0.27
    ohn
    -0.27
     Quant
    -0.26
    ativa
    -0.26
    atern
    -0.26
     CHO
    -0.25
    ç»´å¥ĩ
    -0.25
    Quant
    -0.25
     cant
    -0.25
    POSITIVE LOGITS
     Witnesses
    0.27
     witnesses
    0.27
    _average
    0.26
    åİŁæłĩé¢ĺ
    0.26
    lessly
    0.26
    åŀ£
    0.25
     average
    0.25
     Average
    0.25
    baugh
    0.25
    ãĥĽãĥ¼ãĥł
    0.25
    Act Density 0.012%

    No Known Activations