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

    Neuronpedia

    INDEX
    Explanations

    detection and technical requirements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    াইজ
    0.43
     ense
    0.40
     pronoun
    0.39
     noi
    0.39
    чала
    0.39
     glimps
    0.38
     Appraisal
    0.38
     filt
    0.38
     noirs
    0.38
     purses
    0.38
    POSITIVE LOGITS
    agr
    0.40
    alı
    0.39
    ypen
    0.39
    ptid
    0.38
    asy
    0.38
     फॉरेस्ट
    0.37
     फ्यूचर
    0.37
    מור
    0.37
     時
    0.36
    尽可能
    0.36
    Act Density 0.000%

    No Known Activations