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

    Neuronpedia

    INDEX
    Explanations

    competitions and voting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (fb
    -0.07
     Tucson
    -0.06
     Prof
    -0.06
    -(
    -0.06
     authored
    -0.06
     defin
    -0.06
     defended
    -0.06
     haya
    -0.06
     ethnic
    -0.06
     muchas
    -0.06
    POSITIVE LOGITS
    "},"
    0.07
    bestos
    0.07
    kola
    0.07
     Granted
    0.06
     additive
    0.06
    改革
    0.06
     İng
    0.06
    .socket
    0.06
    arton
    0.06
     sucker
    0.06
    Act Density 0.007%

    No Known Activations