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

    Neuronpedia

    INDEX
    Explanations

    locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    animals
    -0.07
    618
    -0.07
    ”
    -0.06
    .res
    -0.06
    SSH
    -0.06
    -Cs
    -0.06
    uran
    -0.06
    \web
    -0.06
    fant
    -0.06
    ted
    -0.06
    POSITIVE LOGITS
    (center
    0.07
     AlertDialog
    0.06
    ([-
    0.06
    ROLS
    0.06
     tik
    0.06
     bezier
    0.06
    !↵↵↵↵↵↵
    0.06
    。↵↵↵↵↵↵
    0.06
    ')],↵
    0.06
    ],&
    0.06
    Act Density 0.103%

    No Known Activations