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

    Neuronpedia

    INDEX
    Explanations

    Blogger comments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .is
    -0.07
    需
    -0.06
    允
    -0.06
    -mode
    -0.06
    нулась
    -0.06
    cycles
    -0.06
    Atom
    -0.06
    (Xml
    -0.06
     유형
    -0.06
     commenter
    -0.06
    POSITIVE LOGITS
     işe
    0.07
    552
    0.07
    ('');↵
    0.07
     elekt
    0.07
    GRE
    0.06
    _ATTACHMENT
    0.06
    [mid
    0.06
     バ
    0.06
    ็กซ
    0.06
    _LANE
    0.06
    Act Density 0.004%

    No Known Activations