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

    Neuronpedia

    INDEX
    Explanations

    parameter names and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ặp
    0.37
    两个人
    0.37
    ште
    0.36
    ცი
    0.35
    อม
    0.35
    चने
    0.34
    둣
    0.34
     preocupación
    0.34
    혈
    0.34
    嬿
    0.34
    POSITIVE LOGITS
    __
    0.48
     _
    0.46
     __
    0.42
     remarks
    0.41
    allow
    0.41
    name
    0.40
     name
    0.40
     friendly
    0.39
     impairment
    0.38
     imput
    0.38
    Act Density 0.008%

    No Known Activations