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

    Neuronpedia

    INDEX
    Explanations

    Technology news articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    创伤
    -0.08
    初三
    -0.07
    周四
    -0.07
    各
    -0.07
     Northwestern
    -0.07
    UC
    -0.07
     interp
    -0.07
     Ste
    -0.07
    ’in
    -0.07
     mailed
    -0.07
    POSITIVE LOGITS
    갯
    0.08
    CHandle
    0.08
    DEFAULT
    0.07
    خف
    0.07
    DEVICE
    0.07
    unity
    0.07
    essian
    0.07
    .."
    0.07
    .linspace
    0.07
    ANCH
    0.07
    Act Density 0.003%

    No Known Activations