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

    Neuronpedia

    INDEX
    Explanations

    here

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    吓
    -0.07
     Eve
    -0.07
     perpet
    -0.07
    ovi
    -0.06
     Fut
    -0.06
     downloaded
    -0.06
    .Utc
    -0.06
    ʝ
    -0.06
    舢
    -0.06
    我觉得
    -0.06
    POSITIVE LOGITS
    .getDefault
    0.07
     DEVICE
    0.07
     참고
    0.07
    VOICE
    0.07
    гал
    0.06
    _Create
    0.06
    率领
    0.06
    阍
    0.06
    ')]
    0.06
    attribute
    0.06
    Act Density 0.005%

    No Known Activations