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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (void
    -0.07
     parsed
    -0.06
     avenues
    -0.06
    Toe
    -0.06
    conversion
    -0.06
     dav
    -0.06
     safety
    -0.06
     Force
    -0.06
    coding
    -0.06
     erosion
    -0.06
    POSITIVE LOGITS
    strpos
    0.08
    fieldName
    0.08
     sửa
    0.06
     lr
    0.06
    σεων
    0.06
    intosh
    0.06
    (Server
    0.06
     StatusBar
    0.06
    醴
    0.06
     Enh
    0.06
    Act Density 0.002%

    No Known Activations