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

    Neuronpedia

    INDEX
    Explanations

    lock

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iox
    -0.08
    ucid
    -0.08
    openid
    -0.07
    elsk
    -0.07
    -0.07
    ø
    -0.07
     openly
    -0.07
    intha
    -0.07
     supplementation
    -0.07
    izon
    -0.07
    POSITIVE LOGITS
    起来
    0.09
     automatique
    0.09
     automática
    0.08
     automatiquement
    0.08
    自动
    0.08
     jb
    0.08
     Collapse
    0.08
    Chats
    0.08
     automático
    0.08
     автоматически
    0.08
    Act Density 0.009%
    No Known Activations