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

    Neuronpedia

    INDEX
    Explanations

    implied

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     trans
    -0.07
     parsers
    -0.07
     disb
    -0.06
     Ко
    -0.06
    (".
    -0.06
     endDate
    -0.06
     виступ
    -0.06
    材料
    -0.06
     condiciones
    -0.06
     div
    -0.06
    POSITIVE LOGITS
     подс
    0.07
    /catalog
    0.07
    ilder
    0.06
    rogram
    0.06
     υπ
    0.06
    noopener
    0.06
    sher
    0.06
    Arrow
    0.06
     Officials
    0.06
     commuter
    0.06
    Act Density 0.004%

    No Known Activations