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

    Neuronpedia

    INDEX
    Explanations

    company names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kö
    -0.07
    _IND
    -0.07
    -0.06
    히
    -0.06
    (builder
    -0.06
     Fallen
    -0.06
    にも
    -0.06
    -0.06
    يلا
    -0.06
    貨
    -0.06
    POSITIVE LOGITS
     Infect
    0.07
     Ethics
    0.07
    licken
    0.07
    मत
    0.07
     vocational
    0.07
     قوان
    0.07
     uniform
    0.06
    APE
    0.06
    -blocking
    0.06
     Princeton
    0.06
    Act Density 0.004%

    No Known Activations