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

    Neuronpedia

    INDEX
    Explanations

    habit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zem
    -0.07
    .Pow
    -0.07
    економ
    -0.07
     плен
    -0.06
     IR
    -0.06
    untary
    -0.06
     entropy
    -0.06
    elin
    -0.06
     karşılaş
    -0.06
     نشان
    -0.06
    POSITIVE LOGITS
     vigil
    0.07
     habit
    0.07
     elephants
    0.06
     invit
    0.06
    zych
    0.06
     fif
    0.06
    ploy
    0.06
    شف
    0.06
    DataExchange
    0.06
    .firstName
    0.06
    Act Density 0.018%

    No Known Activations