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

    Neuronpedia

    INDEX
    Explanations

    200

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DataFrame
    -0.07
    를
    -0.06
     chaining
    -0.06
    Themes
    -0.06
     slopes
    -0.06
    IH
    -0.06
    的情
    -0.06
    Fair
    -0.06
     ON
    -0.06
     Fair
    -0.06
    POSITIVE LOGITS
     プ
    0.06
     nipples
    0.06
     Antonio
    0.06
    _blend
    0.06
    _EDITOR
    0.06
     �
    0.06
    超过
    0.06
    patible
    0.06
    _TIM
    0.05
     algunas
    0.05
    Act Density 0.014%

    No Known Activations