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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names and affiliations

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

    Dr names and tests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CloseOperation
    -0.47
     SwitchCompat
    -0.44
     مشين
    -0.43
    -
    -0.42
    imdi
    -0.40
    ism
    -0.40
    TextHelper
    -0.39
    clearfix
    -0.38
     sánh
    -0.38
    сп
    -0.38
    POSITIVE LOGITS
     äusser
    0.66
     optimise
    0.64
     customise
    0.62
     organisers
    0.59
    bibfield
    0.59
     gröss
    0.59
     realise
    0.58
    Şi
    0.57
     perchè
    0.57
     maximise
    0.56
    Act Density 0.118%

    No Known Activations