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

    Neuronpedia

    INDEX
    Explanations

    floating point numbers (or code snippets containing them)

    oai_token-act-pair · gemini-2.0-flash

    binary numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    __":
    -0.84
    __':
    -0.76
    setVerticalGroup
    -0.73
    /**
    -0.70
    =$?
    -0.70
    mappedBy
    -0.68
    endpush
    -0.66
    CppMethod
    -0.66
     onOptions
    -0.63
    -0.62
    POSITIVE LOGITS
    .)
    0.78
    .
    0.68
    .,
    0.63
    .—
    0.60
    .-
    0.60
    .’
    0.57
    .»
    0.56
     nakalista
    0.56
    .'
    0.55
    .]
    0.55
    Act Density 2.644%

    No Known Activations