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

    Neuronpedia

    INDEX
    Explanations

    decimal numbers or periods in text

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

    Code followed by specific methods/properties

    np_acts-logits-general · gemini-2.0-flash

    programming function/method names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     OMITBAD
    -0.88
     ivelany
    -0.85
    SharedCtor
    -0.85
     referenties
    -0.83
    __':
    -0.79
     متعلقه
    -0.76
     صوتيه
    -0.75
    GEBURTSDATUM
    -0.74
    مصادر
    -0.74
     հղումներ
    -0.74
    POSITIVE LOGITS
    ésult
    0.66
    ".$_
    0.64
    eſ
    0.64
    spreis
    0.60
    componentWill
    0.58
    iffance
    0.56
    korb
    0.54
    pecially
    0.53
    ſa
    0.52
    LEIA
    0.52
    Act Density 0.071%

    No Known Activations