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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xce
    -0.06
    他們
    -0.06
     Lose
    -0.06
     человек
    -0.05
    ávání
    -0.05
     transformative
    -0.05
     используется
    -0.05
    iado
    -0.05
     alarak
    -0.05
    _ACCOUNT
    -0.05
    POSITIVE LOGITS
    GI
    0.08
    IPAddress
    0.07
    Dist
    0.07
    SYS
    0.07
     horrible
    0.07
    Hi
    0.07
    !!↵↵
    0.07
    BUG
    0.07
    medi
    0.07
     sehen
    0.06
    Act Density 0.004%

    No Known Activations