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

    Neuronpedia

    INDEX
    Explanations

    Code/technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    circ
    -0.07
     kick
    -0.07
    札
    -0.07
     нор
    -0.07
     rentals
    -0.07
     وس
    -0.06
    καν
    -0.06
    _COOKIE
    -0.06
    ?>>
    -0.06
     volley
    -0.06
    POSITIVE LOGITS
     polyline
    0.07
     sistemi
    0.07
     watcher
    0.06
    -inflammatory
    0.06
    ollision
    0.06
    ("\\
    0.06
     ''↵
    0.06
    _reports
    0.06
    _RESOLUTION
    0.06
    resolve
    0.06
    Act Density 0.001%

    No Known Activations