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

    Neuronpedia

    INDEX
    Explanations

    ALS

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     noble
    -0.07
     отправ
    -0.06
    comed
    -0.06
    Medium
    -0.06
     rar
    -0.06
    similar
    -0.06
     mir
    -0.06
     nob
    -0.06
    <QString
    -0.06
     tents
    -0.06
    POSITIVE LOGITS
    阶段
    0.06
    rg
    0.06
    асс
    0.06
    ĞI
    0.06
     Winchester
    0.06
    _members
    0.06
    (attribute
    0.06
    TAG
    0.06
     upgrade
    0.06
    UG
    0.06
    Act Density 0.001%

    No Known Activations