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

    Neuronpedia

    INDEX
    Explanations

    free

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rapid
    -0.07
     _("
    -0.07
     Sensor
    -0.06
     REPORT
    -0.06
     bots
    -0.06
    ，说
    -0.06
    gL
    -0.06
    _dependency
    -0.06
     Ident
    -0.06
    /ne
    -0.06
    POSITIVE LOGITS
     free
    0.07
    FREE
    0.07
     Damien
    0.07
     ridicule
    0.06
     Free
    0.06
     FREE
    0.06
    ژ
    0.06
     hå
    0.06
    FileStream
    0.06
    free
    0.06
    Act Density 0.012%

    No Known Activations