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

    Neuronpedia

    INDEX
    Explanations

    varied text styles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    STATE
    -0.08
     üstün
    -0.07
    OTP
    -0.07
     sip
    -0.07
     surpr
    -0.07
    激动
    -0.06
    INY
    -0.06
    asmus
    -0.06
    >ID
    -0.06
     заболевания
    -0.06
    POSITIVE LOGITS
     $.
    0.07
    $r
    0.06
     Alvarez
    0.06
    复印件
    0.06
     Store
    0.06
    ⅀
    0.06
     remedies
    0.06
    ApiKey
    0.06
    岔
    0.06
    建材
    0.06
    Act Density 0.184%

    No Known Activations