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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation in LaTeX

    oai_token-act-pair · gemini-2.0-flash

    Math equations with smallcaps

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     &___
    -0.73
    parsedMessage
    -0.68
    LookAnd
    -0.67
    OrBuilder
    -0.65
    CppMethod
    -0.57
    Descriere
    -0.55
    /**
    -0.55
     betweenstory
    -0.54
    parametrize
    -0.54
     Infórmanos
    -0.54
    POSITIVE LOGITS
    mo
    0.65
    gey
    0.52
    gatsby
    0.48
    protoimpl
    0.47
     bande
    0.47
    ge
    0.46
    mfenced
    0.46
    square
    0.45
    sterone
    0.45
    taz
    0.45
    Act Density 2.306%

    No Known Activations