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

    Neuronpedia

    INDEX
    Explanations

    into three / using Base

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     như
    0.35
    ス
    0.34
     и
    0.32
     université
    0.32
     giữ
    0.32
     họ
    0.32
     църква
    0.32
    𝕝
    0.31
     sri
    0.31
    、
    0.31
    POSITIVE LOGITS
    ب
    0.42
    ين
    0.42
    f
    0.41
    ed
    0.36
    ad
    0.35
    at
    0.34
    ים
    0.33
    ból
    0.32
    m
    0.32
    ด
    0.32
    Act Density 1.005%

    No Known Activations