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

    Neuronpedia

    INDEX
    Explanations

    code snippets with 'compact' and html

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NUMX
    -0.91
    __':
    -0.90
    +#+#
    -0.85
    saraba
    -0.84
    tagHelperRunner
    -0.84
     itſelf
    -0.82
     '\\;'
    -0.81
    OGND
    -0.81
    AndEndTag
    -0.78
    '}>
    -0.78
    POSITIVE LOGITS
    ,
    0.55
     -
    0.54
    ↵↵↵
    0.49
    .
    0.45
     er
    0.44
    walde
    0.44
    ss
    0.43
    felde
    0.43
    0.43
     l
    0.43
    Act Density 0.160%

    No Known Activations