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

    Neuronpedia

    INDEX
    Explanations

    clickbait titles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dimensions
    -0.07
     visual
    -0.06
    Company
    -0.06
    abling
    -0.06
    istrat
    -0.06
     developing
    -0.06
    -lines
    -0.06
    actly
    -0.06
     rooms
    -0.06
     legislature
    -0.06
    POSITIVE LOGITS
     должно
    0.07
    _ComCallableWrapper
    0.07
     okum
    0.07
    noxious
    0.06
     少
    0.06
     subur
    0.06
    CursorPosition
    0.06
     $__
    0.06
    čný
    0.06
    MN
    0.06
    Act Density 0.042%

    No Known Activations