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

    Neuronpedia

    INDEX
    Explanations

    characterization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Laws
    -0.07
    .ToUpper
    -0.07
     brightness
    -0.06
    OfWork
    -0.06
     nylon
    -0.06
     VLC
    -0.06
    Have
    -0.06
    .task
    -0.06
     dishwasher
    -0.06
     ESL
    -0.06
    POSITIVE LOGITS
     characterized
    0.08
    ิงห
    0.07
    atform
    0.07
     /^[
    0.07
     optimize
    0.07
     Candid
    0.07
     characterization
    0.07
     characterize
    0.07
    imiter
    0.06
    อเร
    0.06
    Act Density 0.015%

    No Known Activations