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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     responsable
    -0.06
    acente
    -0.06
    setDefault
    -0.06
     Hindu
    -0.06
     Nature
    -0.06
    如
    -0.06
    Overview
    -0.06
    elow
    -0.06
    aticon
    -0.06
    rule
    -0.05
    POSITIVE LOGITS
    laughs
    0.07
    UILT
    0.07
    .AC
    0.07
    อกจากน
    0.07
    ilen
    0.07
     (--
    0.06
    _activities
    0.06
    .SelectCommand
    0.06
    ROAD
    0.06
    وگر
    0.06
    Act Density 0.064%

    No Known Activations