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

    Neuronpedia

    INDEX
    Explanations

    direct or install

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    heets
    0.54
     realise
    0.45
     brengen
    0.44
    sheets
    0.44
     první
    0.44
    鏻
    0.43
    ⺈
    0.43
    一开始
    0.42
    Een
    0.42
     جر
    0.42
    POSITIVE LOGITS
    mu
    0.44
    idi
    0.40
    AM
    0.40
     (-
    0.40
    anyi
    0.40
    qda
    0.40
     lucid
    0.40
    checkbox
    0.40
    suz
    0.39
     暗
    0.39
    Act Density 0.009%

    No Known Activations