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

    Neuronpedia

    INDEX
    Explanations

    unlock potential

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    嘉宾
    0.52
     దేవ
    0.48
     NULL
    0.46
     Distinct
    0.45
    ０
    0.44
    规则
    0.43
     Jodi
    0.43
    Account
    0.43
    Distinct
    0.42
     Свя
    0.41
    POSITIVE LOGITS
     সুখ
    0.48
     carburetor
    0.47
     carbohydrate
    0.46
    aried
    0.46
    eh
    0.46
     biologie
    0.46
    h
    0.46
    nonlinear
    0.45
    vä
    0.45
    カロ
    0.45
    Act Density 0.003%

    No Known Activations