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

    Neuronpedia

    INDEX
    Explanations

    generate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    346
    -0.07
     Survival
    -0.07
    Memo
    -0.06
     sobre
    -0.06
    _car
    -0.06
    lıklı
    -0.06
    .num
    -0.06
    (TM
    -0.06
     дор
    -0.06
     уз
    -0.06
    POSITIVE LOGITS
     Glenn
    0.07
     dangling
    0.07
     بانک
    0.06
    .HOUR
    0.06
    tras
    0.06
    _GENER
    0.06
     pokus
    0.06
     раб
    0.06
    )에
    0.06
    िजल
    0.06
    Act Density 0.266%

    No Known Activations