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

    Neuronpedia

    INDEX
    Explanations

    emojis and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    File
    0.44
    ms
    0.44
     General
    0.43
    K
    0.42
    pre
    0.42
    Suite
    0.41
    Class
    0.41
    General
    0.41
    0
    0.41
    를
    0.41
    POSITIVE LOGITS
     divergents
    0.50
    コスト
    0.50
    াদা
    0.49
     ಮಹಿ
    0.49
     schauen
    0.48
     واپس
    0.48
     勝
    0.48
     calmed
    0.48
    duplicates
    0.48
     ближай
    0.48
    Act Density 0.004%

    No Known Activations