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

    Neuronpedia

    INDEX
    Explanations

    java 8

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﻁ
    0.50
    ის
    0.48
    મના
    0.48
    き
    0.47
    тных
    0.47
    𝘬
    0.47
    ونها
    0.46
    کي
    0.46
     keseluruhan
    0.45
    کور
    0.44
    POSITIVE LOGITS
    0
    0.59
    o
    0.57
    ge
    0.53
    ir
    0.53
    1
    0.52
    ca
    0.51
     in
    0.48
    va
    0.46
    cé
    0.46
    e
    0.45
    Act Density 0.000%

    No Known Activations