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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /rules
    -0.07
    .metroLabel
    -0.06
    ：
    -0.06
    ................................
    -0.06
     Сп
    -0.06
    .BorderStyle
    -0.06
     Benedict
    -0.06
    .localizedDescription
    -0.06
    (media
    -0.06
    /dat
    -0.06
    POSITIVE LOGITS
     cara
    0.06
    wallet
    0.06
    Outputs
    0.06
     pantalla
    0.06
    ový
    0.06
     techno
    0.06
    Ì
    0.06
     institutes
    0.06
     Hitler
    0.06
     homem
    0.06
    Act Density 0.000%

    No Known Activations