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

    Neuronpedia

    INDEX
    Explanations

    Company information and links

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     laundry
    -0.06
     SQUARE
    -0.06
    (|
    -0.06
     Kenn
    -0.06
     offspring
    -0.06
     Iron
    -0.06
    neider
    -0.06
    598
    -0.06
    ينة
    -0.06
     primaries
    -0.06
    POSITIVE LOGITS
    comma
    0.08
    _found
    0.07
    	mod
    0.07
     Gerard
    0.06
    میر
    0.06
     fucks
    0.06
    layers
    0.06
    .#
    0.06
    ประส
    0.06
    ично
    0.06
    Act Density 0.007%

    No Known Activations