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

    Neuronpedia

    INDEX
    Explanations

    198

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Exhibition
    -0.06
    erosis
    -0.06
    ihat
    -0.06
    asel
    -0.06
     ccp
    -0.06
    .Common
    -0.06
    07
    -0.06
     Т
    -0.06
     Merkel
    -0.06
    moid
    -0.06
    POSITIVE LOGITS
     amat
    0.07
    alış
    0.07
     promoting
    0.06
     violate
    0.06
     नक
    0.06
    .predict
    0.06
     Criminal
    0.06
    contexts
    0.06
    (visitor
    0.06
     anlayış
    0.06
    Act Density 0.002%

    No Known Activations