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

    Neuronpedia

    INDEX
    Explanations

    image url or photo

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stops
    0.87
     stop
    0.86
     only
    0.82
     बारह
    0.80
     Stop
    0.78
     hides
    0.78
     ten
    0.78
     screech
    0.76
     recovers
    0.76
     backward
    0.76
    POSITIVE LOGITS
    Foto
    0.79
     چل
    0.72
    ევ
    0.72
    ertung
    0.71
     mergeddata
    0.71
    ർന്ന
    0.71
    사진
    0.69
    untes
    0.69
     അവ
    0.69
    olded
    0.69
    Act Density 0.002%

    No Known Activations