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

    Neuronpedia

    INDEX
    Explanations

    Code and citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GenerationType
    -0.56
    WriteBarrier
    -0.56
    بوابة
    -0.54
    opsida
    -0.51
    DIRS
    -0.50
    Compiler
    -0.49
    orial
    -0.49
    BagLayout
    -0.48
    метров
    -0.48
    шка
    -0.47
    POSITIVE LOGITS
    ValueStyle
    0.82
    脚注の使い方
    0.65
    ябре
    0.59
    __(/*!
    0.59
     GIPHY
    0.59
    IsMutable
    0.58
     gesche
    0.56
     antaranya
    0.55
     okuyayım
    0.54
    berdayakan
    0.54
    Act Density 0.001%

    No Known Activations