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

    Neuronpedia

    INDEX
    Explanations

    service

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    advisor
    -0.07
    chef
    -0.07
    abay
    -0.06
    بصر
    -0.06
    为准
    -0.06
    _range
    -0.06
    蟋
    -0.06
     показ
    -0.06
    �
    -0.06
    珂
    -0.06
    POSITIVE LOGITS
     Redirect
    0.07
    bind
    0.07
     Init
    0.07
    뼛
    0.07
     Sanity
    0.07
    ITA
    0.07
    应用场景
    0.06
    ISTICS
    0.06
    aptic
    0.06
    "},"
    0.06
    Act Density 0.002%

    No Known Activations