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

    Neuronpedia

    INDEX
    Explanations

    settings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mam
    -0.08
     maize
    -0.07
    422
    -0.07
    758
    -0.07
     Colombia
    -0.07
     nuclei
    -0.07
     Biography
    -0.07
     pop
    -0.07
    up
    -0.07
    Cargo
    -0.07
    POSITIVE LOGITS
     settings
    0.10
    (settings
    0.09
     Settings
    0.09
    .settings
    0.08
    Settings
    0.08
     setting
    0.07
     эт
    0.07
     همین
    0.07
    ัก
    0.07
    VIOUS
    0.07
    Act Density 0.020%

    No Known Activations