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

    Neuronpedia

    INDEX
    Explanations

    effort and creation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dat
    -0.07
    赵
    -0.07
     عن
    -0.06
    pcodes
    -0.06
     ViewState
    -0.06
    payload
    -0.06
    IMITIVE
    -0.06
     mostra
    -0.06
     futile
    -0.06
    _vec
    -0.06
    POSITIVE LOGITS
     सभ
    0.06
     Henry
    0.06
     NASA
    0.06
     until
    0.06
     Tud
    0.06
    水
    0.06
    सभ
    0.06
    覆
    0.06
     DEBUG
    0.06
    _plate
    0.06
    Act Density 0.228%

    No Known Activations