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

    Neuronpedia

    INDEX
    Explanations

    People and their roles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cortisol
    -0.06
     报
    -0.06
    .pow
    -0.06
     radios
    -0.06
    arrings
    -0.06
    OLOR
    -0.06
    closest
    -0.06
     earrings
    -0.06
    /light
    -0.06
     RCA
    -0.06
    POSITIVE LOGITS
    .calls
    0.07
     clot
    0.06
     obrov
    0.06
    _instruction
    0.06
     अब
    0.06
    oauth
    0.06
     Hải
    0.06
    ậ
    0.06
    assandra
    0.06
     tranh
    0.06
    Act Density 0.043%

    No Known Activations