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

    Neuronpedia

    INDEX
    Explanations

    The number 1728

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dam
    -0.08
     Schatten
    -0.08
    -0.08
     Camer
    -0.08
     остальных
    -0.07
     hm
    -0.07
     rek
    -0.07
    ฟ
    -0.07
    beaut
    -0.07
     сю
    -0.07
    POSITIVE LOGITS
    须
    0.08
    metro
    0.07
    ਦੀ
    0.07
    .inventory
    0.07
    appro
    0.07
     sein
    0.07
    航
    0.07
    'ok
    0.07
    isk
    0.07
     ਬ
    0.07
    Act Density 0.021%
    No Known Activations