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

    Neuronpedia

    INDEX
    Explanations

    verification

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _qos
    -0.07
    .Initialize
    -0.06
    banana
    -0.06
     Woche
    -0.06
    غان
    -0.06
    犬
    -0.06
    』↵↵
    -0.06
    üyorum
    -0.06
     روسی
    -0.06
    FW
    -0.06
    POSITIVE LOGITS
     nå
    0.06
    lett
    0.06
    /sources
    0.06
     ads
    0.06
     dum
    0.06
    _display
    0.06
    ,“
    0.06
     influence
    0.06
    '</
    0.06
     accountant
    0.06
    Act Density 0.027%

    No Known Activations