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

    Neuronpedia

    INDEX
    Explanations

    string

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    )*(
    -0.07
    modes
    -0.06
    ्वय
    -0.06
    tech
    -0.06
    payment
    -0.06
    ной
    -0.06
    ":@"
    -0.06
    allenges
    -0.06
     ect
    -0.06
    [date
    -0.06
    POSITIVE LOGITS
    ゼ
    0.07
     deserves
    0.07
     पहच
    0.06
    Rua
    0.06
    _FREQ
    0.06
     RETURN
    0.06
     já
    0.06
     mỗi
    0.06
    ｿ
    0.06
    umeric
    0.06
    Act Density 0.015%

    No Known Activations