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

    Neuronpedia

    INDEX
    Explanations

    introduces code explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     기본적인
    0.56
     कुछ
    0.49
     Somewhat
    0.47
     somewhat
    0.46
     मामूली
    0.46
     조금
    0.45
     थोड़ी
    0.45
     unimportant
    0.44
    いくつか
    0.44
    了一些
    0.43
    POSITIVE LOGITS
    THIS
    0.50
     THIS
    0.48
    全新的
    0.48
     véritable
    0.48
     escánd
    0.48
     diesem
    0.47
     autént
    0.46
     FULL
    0.46
    این
    0.46
     NEW
    0.45
    Act Density 0.243%

    No Known Activations