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

    Neuronpedia

    INDEX
    Explanations

    go package main

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    高志森
    0.46
    軗
    0.46
    𒆠
    0.46
    \}}\
    0.45
    堈
    0.45
    蠵
    0.45
    vrdr
    0.45
    alesi
    0.44
    namefont
    0.43
    Repr
    0.43
    POSITIVE LOGITS
     main
    0.61
     controller
    0.53
     util
    0.52
     J
    0.51
     class
    0.50
     sys
    0.49
     classes
    0.48
     server
    0.47
     j
    0.47
     books
    0.46
    Act Density 0.000%

    No Known Activations