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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    631
    -0.07
     bed
    -0.06
    inspection
    -0.06
    madığı
    -0.06
     Compar
    -0.06
     ❤
    -0.06
    ewater
    -0.06
    fang
    -0.06
     bw
    -0.06
    орів
    -0.06
    POSITIVE LOGITS
    ----↵
    0.07
    acion
    0.07
     relaciones
    0.07
    (power
    0.07
     Deals
    0.06
    (columns
    0.06
     instruments
    0.06
    ापस
    0.06
    가격
    0.06
     Trio
    0.06
    Act Density 0.000%

    No Known Activations