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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    932
    -0.07
    _stage
    -0.07
    }/{
    -0.07
    lets
    -0.07
    279
    -0.07
     сейчас
    -0.06
     BLE
    -0.06
    ozřejmě
    -0.06
     quindi
    -0.06
    ')</
    -0.06
    POSITIVE LOGITS
     strawberries
    0.07
     خدم
    0.06
    lant
    0.06
     Hook
    0.06
    .factory
    0.06
     mov
    0.06
    .*↵↵
    0.06
     getSupportActionBar
    0.06
    اجر
    0.06
     Doming
    0.06
    Act Density 0.009%

    No Known Activations