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

    Neuronpedia

    INDEX
    Explanations

    instances of a specific syntax or structure in the text, particularly related to data formatting or programming-like notation

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

    <start_of_turn>user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     digress
    -0.38
     embaraz
    -0.38
     felicitación
    -0.37
     Schul
    -0.37
    cakup
    -0.37
     adota
    -0.36
     peito
    -0.36
     Schluss
    -0.36
    élément
    -0.36
    raszamy
    -0.35
    POSITIVE LOGITS
    disposing
    1.13
    ंदीखरीदारी
    0.79
     Roskov
    0.76
    IVEREF
    0.75
     beginnetje
    0.66
    الحياه
    0.63
    FunctionFlags
    0.62
     defaultstate
    0.61
    Хьажоргаш
    0.60
    localctx
    0.59
    Act Density 0.000%

    No Known Activations