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

    Neuronpedia

    INDEX
    Explanations

    For

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     />,↵
    -0.06
    _week
    -0.06
    пион
    -0.06
    .End
    -0.06
     penal
    -0.06
    }}],↵
    -0.06
    เก
    -0.06
    ))),↵
    -0.06
    _LINES
    -0.06
     Above
    -0.06
    POSITIVE LOGITS
     derin
    0.07
    (display
    0.06
     whit
    0.06
    李
    0.06
    <Object
    0.06
    private
    0.06
     huy
    0.06
     Adventures
    0.06
    (Name
    0.06
     jouer
    0.06
    Act Density 0.002%

    No Known Activations