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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vana
    -0.08
    已经成为
    -0.07
    无障碍
    -0.07
     News
    -0.07
    _ready
    -0.07
    来形容
    -0.06
     babys
    -0.06
    教师
    -0.06
     scrollTo
    -0.06
     meddling
    -0.06
    POSITIVE LOGITS
    AND
    0.07
     sons
    0.07
    and
    0.07
    *
    0.07
    pectives
    0.07
    地说
    0.07
     kp
    0.07
    并
    0.07
    .medium
    0.07
    /-
    0.07
    Act Density 0.051%

    No Known Activations