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

    Neuronpedia

    INDEX
    Explanations

    options 1 or 2

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    0.64
    j
    0.58
     stric
    0.56
    ي
    0.54
     '^
    0.53
    ad
    0.52
     seria
    0.51
     importa
    0.51
     proofs
    0.50
    ceding
    0.50
    POSITIVE LOGITS
    ған
    0.59
    ंग
    0.56
    ﺒ
    0.56
    ﻊ
    0.54
    િસ્
    0.48
    ﻔ
    0.48
     બની
    0.44
    ﺤ
    0.44
     concentrate
    0.44
    mood
    0.44
    Act Density 0.197%

    No Known Activations