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

    Neuronpedia

    INDEX
    Explanations

    take, capture

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     모델
    -0.07
    technical
    -0.07
    verages
    -0.07
    анти
    -0.06
     domains
    -0.06
    Domains
    -0.06
     reward
    -0.06
     oid
    -0.06
    ylene
    -0.06
    urrencies
    -0.06
    POSITIVE LOGITS
     fanc
    0.06
     Gron
    0.06
    <TSource
    0.06
    tah
    0.05
    menuItem
    0.05
    VPN
    0.05
    TabControl
    0.05
    _UTILS
    0.05
     prostituerte
    0.05
     OCD
    0.05
    Act Density 0.073%

    No Known Activations