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

    Neuronpedia

    INDEX
    Explanations

    javascript functions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     motif
    -0.08
    ताओं
    -0.08
     Mathemat
    -0.08
     numerator
    -0.07
     mathematic
    -0.07
     textbook
    -0.07
     epit
    -0.07
    irio
    -0.07
     conocido
    -0.07
     príncipe
    -0.07
    POSITIVE LOGITS
     jub
    0.09
     Louise
    0.09
    (target
    0.08
    ieger
    0.08
    krift
    0.08
     ressent
    0.08
     થતાં
    0.08
    Toggle
    0.07
     kc
    0.07
     Respir
    0.07
    Act Density 0.002%

    No Known Activations