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

    Neuronpedia

    INDEX
    Explanations

    road directions and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    >\<^
    0.43
     \%
    0.36
     dechlorination
    0.35
     ကျွန်
    0.35
     ሌሎች
    0.34
     compréhension
    0.33
    📻
    0.32
     أحد
    0.32
     בין
    0.32
     dalších
    0.32
    POSITIVE LOGITS
    c
    0.41
    k
    0.38
    v
    0.38
    san
    0.38
    ar
    0.38
    i
    0.37
    ﻛ
    0.37
    ta
    0.37
    src
    0.37
    sur
    0.37
    Act Density 0.007%

    No Known Activations