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

    Neuronpedia

    INDEX
    Explanations

    XML namespaces, XAML

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    رید
    0.38
    橐
    0.37
     Bikes
    0.37
     bowled
    0.37
     Tutak
    0.36
    Ḵ
    0.36
     इनवर्स
    0.36
    秅
    0.36
     एक्सरसाइज
    0.35
    ায়ী
    0.35
    POSITIVE LOGITS
    Transcription
    0.70
     Transcription
    0.63
     transcription
    0.61
    Transcript
    0.59
     transcribe
    0.58
     trans
    0.54
    trans
    0.53
     Transcript
    0.53
     тран
    0.51
     transcript
    0.50
    Act Density 0.000%

    No Known Activations