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

    Neuronpedia

    INDEX
    Explanations

    use

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tara
    -0.07
    켜
    -0.06
    بود
    -0.06
     quân
    -0.06
     zaman
    -0.06
    leen
    -0.06
     کردن
    -0.06
    _boundary
    -0.06
     Robert
    -0.06
     زاد
    -0.06
    POSITIVE LOGITS
    itty
    0.07
     paused
    0.07
    ंक
    0.06
     utilizing
    0.06
     utilize
    0.06
    UPER
    0.06
     jsou
    0.06
    ITTER
    0.06
    Talk
    0.06
     PIO
    0.06
    Act Density 0.060%

    No Known Activations