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

    Neuronpedia

    INDEX
    Explanations

    code generation and comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.36
    éi
    0.35
    ó
    0.34
    يا
    0.32
    ின்
    0.32
     eros
    0.32
     jú
    0.31
     kleiner
    0.31
    ínu
    0.31
     HMO
    0.31
    POSITIVE LOGITS
    I
    0.56
    C
    0.51
    ﻭ
    0.48
    ların
    0.47
    R
    0.47
    B
    0.46
    M
    0.45
    ه
    0.44
    D
    0.43
    ،
    0.43
    Act Density 0.009%

    No Known Activations