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

    Neuronpedia

    INDEX
    Explanations

    software and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    0.76
    מ
    0.73
    SP
    0.71
     গান্ধ
    0.70
     Lymph
    0.70
     हाता
    0.68
     reson
    0.67
    ’
    0.64
     shader
    0.64
     অঞ্জ
    0.64
    POSITIVE LOGITS
    ی
    0.98
    ેટ
    0.86
    獗
    0.82
    cartes
    0.81
    くれた
    0.79
    یل
    0.77
     notori
    0.77
    يرة
    0.77
    வுக்கு
    0.75
    प्टन
    0.75
    Act Density 0.005%

    No Known Activations