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

    Neuronpedia

    INDEX
    Explanations

    queries or requests for help or advice

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

    "Has," "Does," "Can," "If" followed by a question

    np_acts-logits-general · gemini-2.0-flash

    auxiliary verb + anyone/anybody

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    onViewCreated
    -0.72
    Personendaten
    -0.69
    Vidite
    -0.68
     noqa
    -0.64
     étoient
    -0.63
    Javadoc
    -0.63
     ouvriers
    -0.62
     AspNetCore
    -0.62
    ########.
    -0.62
    nonatomic
    -0.61
    POSITIVE LOGITS
     anyone
    2.09
     anybody
    1.81
     Anyone
    1.80
    Anyone
    1.78
    anyone
    1.77
     Anybody
    1.75
    Anybody
    1.69
     ANYONE
    1.36
    Alguien
    1.05
     someone
    1.00
    Act Density 0.225%

    No Known Activations