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

    Neuronpedia

    INDEX
    Explanations

    chemical names with numbers and prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NaOH
    0.52
    髅
    0.50
    羮
    0.49
    鞅
    0.48
     زیرمه
    0.48
     नाइट्रेट
    0.48
    gateTime
    0.47
    ﹍
    0.47
    Ყ
    0.46
    徭
    0.46
    POSITIVE LOGITS
    -(
    0.72
     N
    0.64
    -
    0.62
    0.61
    -[
    0.59
    7
    0.59
    trans
    0.58
     p
    0.57
    {\
    0.57
    amin
    0.57
    Act Density 0.014%

    No Known Activations