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

    Neuronpedia

    INDEX
    Explanations

    based on keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     findest
    0.43
    V
    0.43
    TEGER
    0.42
    Find
    0.41
     vergang
    0.41
     Finder
    0.40
     sebelumnya
    0.39
     Muchas
    0.39
     Find
    0.38
     Preferably
    0.38
    POSITIVE LOGITS
    人工
    0.48
    ոն
    0.46
    人の
    0.43
    hrung
    0.43
    arkeit
    0.41
    人之
    0.41
    ára
    0.40
    キーワード
    0.40
    แรม
    0.39
     pantry
    0.38
    Act Density 0.000%

    No Known Activations