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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating effort, preparation, and caution

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

    with proper effort and quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GOTREF
    -0.43
    orElseThrow
    -0.41
     ब्रेकडाउन
    -0.35
     cabecera
    -0.34
    Jereo
    -0.34
    kuper
    -0.33
     namorados
    -0.33
    помним
    -0.32
    NewReader
    -0.32
     Heaton
    -0.31
    POSITIVE LOGITS
    jspb
    0.73
    SharedCtor
    0.60
     autorytatywna
    0.57
     صوتيه
    0.57
    :✨
    0.57
    
    0.55
    +#+#
    0.55
     lizenzfreies
    0.53
     Administrativna
    0.52
     للاسماء
    0.51
    Act Density 0.042%

    No Known Activations