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

    Neuronpedia

    INDEX
    Explanations

    call

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pled
    -0.07
     Illustrated
    -0.07
    .bean
    -0.07
    相似
    -0.07
    热闹
    -0.07
    相声
    -0.07
    _PARTITION
    -0.06
    ский
    -0.06
    ᚖ
    -0.06
     Vere
    -0.06
    POSITIVE LOGITS
    projection
    0.07
    一小
    0.07
    加工厂
    0.07
    追随
    0.07
     Crossing
    0.07
                 ↵
    0.07
    粒
    0.07
    *L
    0.07
    (col
    0.07
    _
↵
↵
    0.06
    Act Density 0.032%

    No Known Activations