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

    Neuronpedia

    INDEX
    Explanations

    generating new forms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Gruppe
    0.40
    ረሻ
    0.38
    シフト
    0.37
     நிர்வாகிகள்
    0.37
    っていく
    0.36
     arrangements
    0.35
     Indy
    0.35
    صحاب
    0.35
     الخمسه
    0.35
    安排
    0.35
    POSITIVE LOGITS
     transform
    0.79
     transforms
    0.77
    transform
    0.75
     Transform
    0.72
     Transforms
    0.71
    Transform
    0.69
    ransform
    0.65
    Transforms
    0.63
     trasform
    0.62
     transforming
    0.62
    Act Density 0.000%

    No Known Activations