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

    Neuronpedia

    INDEX
    Explanations

    [

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ches
    -0.07
    :Register
    -0.06
    .cy
    -0.06
     supplement
    -0.06
     genitals
    -0.06
     spoil
    -0.06
    crow
    -0.06
    (dis
    -0.06
     incarcer
    -0.06
    …………………………………………
    -0.06
    POSITIVE LOGITS
     [
    0.09
    _ONCE
    0.07
     ']
    0.06
    marked
    0.06
    aped
    0.06
     System
    0.06
    .pth
    0.06
    ért
    0.06
    stacles
    0.06
    auled
    0.06
    Act Density 0.031%

    No Known Activations