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

    Neuronpedia

    INDEX
    Explanations

    terms related to formal proofs and scientific results

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

    proof is/was/shows/claims

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.66
    NameInMap
    -0.66
     CreateTagHelper
    -0.64
    getColumnIndex
    -0.63
    AddTagHelper
    -0.60
    verifyException
    -0.60
    InputBorder
    -0.59
    IntoConstraints
    -0.59
     disambiguazione
    -0.55
    aarrggbb
    -0.51
    POSITIVE LOGITS
     flexibilidad
    0.40
    isamment
    0.38
    chieht
    0.37
     ledig
    0.37
     lisäksi
    0.37
     recargable
    0.36
    virano
    0.35
     comunión
    0.34
     liitty
    0.34
     capacidad
    0.34
    Act Density 0.275%

    No Known Activations