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

    Neuronpedia

    INDEX
    Explanations

    academic fields, especially math and science

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AnchorStyles
    -0.87
     myſelf
    -0.83
    ^(@)
    -0.82
     ſeveral
    -0.82
     Houſe
    -0.81
     Efq
    -0.81
     purpoſe
    -0.80
     becauſe
    -0.80
     fhort
    -0.80
     Theſe
    -0.79
    POSITIVE LOGITS
    <bos>
    0.89
     math
    0.74
    math
    0.73
     maths
    0.59
    Math
    0.58
     Math
    0.55
    MathML
    0.55
    Maths
    0.54
    Personendaten
    0.53
     Algebra
    0.52
    Act Density 2.344%

    No Known Activations