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

    Neuronpedia

    INDEX
    Explanations

    code structures and specific tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     NumericVector
    0.46
     halftone
    0.44
     sécr
    0.43
     tử
    0.41
     corne
    0.41
     converging
    0.40
     arter
    0.39
     subtiliter
    0.39
     valorem
    0.39
     concealing
    0.39
    POSITIVE LOGITS
    While
    0.49
    P
    0.48
    Before
    0.46
    People
    0.44
    The
    0.44
    For
    0.43
    Putting
    0.43
    Whether
    0.42
     Babies
    0.42
    8
    0.42
    Act Density 0.000%

    No Known Activations