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

    Neuronpedia

    INDEX
    Explanations

    background

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     campus
    -0.07
     �
    -0.07
    stamp
    -0.07
    zip
    -0.06
    _WARN
    -0.06
    rne
    -0.06
    arge
    -0.06
    Jesus
    -0.06
     Retrieve
    -0.06
    (label
    -0.06
    POSITIVE LOGITS
    _Context
    0.07
     Decompiled
    0.06
     Đặc
    0.06
    atable
    0.06
     bloodstream
    0.06
    istorical
    0.06
    Ú
    0.06
    ousy
    0.06
    _trans
    0.06
    央
    0.06
    Act Density 0.013%

    No Known Activations