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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and structured data representations, particularly matrices and arrays

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    LaTeX matrix environments

    np_acts-logits-general · gemini-2.0-flash

    mathematical arrays and matrices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ‘
    -0.53
     mu
    -0.50
     re
    -0.50
     “
    -0.50
     Reed
    -0.47
    endpush
    -0.46
    ή
    -0.46
     and
    -0.46
    eb
    -0.45
     Cur
    -0.45
    POSITIVE LOGITS
    BeginContext
    0.95
     CreateTagHelper
    0.94
    ViewFeatures
    0.84
    HasForeignKey
    0.83
    enumii
    0.82
     Paglinawan
    0.81
    makeConstraints
    0.79
     MonoBehaviour
    0.77
    ✭✭
    0.75
    EndProject
    0.74
    Act Density 0.113%

    No Known Activations