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

    Neuronpedia

    INDEX
    Explanations

    channel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    增收
    -0.07
    ANDLE
    -0.07
    Mac
    -0.07
    墀
    -0.07
    ColumnName
    -0.07
    キャッシ
    -0.06
    ordin
    -0.06
    氛
    -0.06
     carry
    -0.06
    iffe
    -0.06
    POSITIVE LOGITS
    需要注意
    0.09
    _multip
    0.08
     этот
    0.07
    痴
    0.07
    _vs
    0.07
     depress
    0.07
    濩
    0.07
    мышл
    0.07
     dep
    0.07
    食物
    0.07
    Act Density 0.005%

    No Known Activations