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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting elements in code

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

    java package and library names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſta
    -0.61
     InputDecoration
    -0.60
    parsedMessage
    -0.57
    InitVars
    -0.56
     ſte
    -0.54
    ioutil
    -0.48
    ">—
    -0.47
     Савезне
    -0.46
    󠁴
    -0.45
    mtrl
    -0.45
    POSITIVE LOGITS
     Audiodateien
    0.49
     noiva
    0.44
     kimia
    0.43
    findpost
    0.42
     nadzieję
    0.41
     bendera
    0.40
    Aiheesta
    0.39
     همچنین
    0.39
     terceira
    0.39
     tampoco
    0.39
    Act Density 0.017%

    No Known Activations