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

    Neuronpedia

    INDEX
    Explanations

    about

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    +S
    -0.07
    -support
    -0.07
     Ї
    -0.07
    (Web
    -0.06
    layout
    -0.06
    ,)
    -0.06
     ("<
    -0.06
     Mountains
    -0.06
    -ar
    -0.06
    ""
    -0.06
    POSITIVE LOGITS
    _NATIVE
    0.06
     grads
    0.06
     Moines
    0.06
     porno
    0.06
     داخلی
    0.06
    iatric
    0.06
     ','.
    0.06
     dorsal
    0.06
     gourmet
    0.06
    _gateway
    0.06
    Act Density 0.008%

    No Known Activations