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

    Neuronpedia

    INDEX
    Explanations

    code snippets containing the word "expect"

    oai_token-act-pair · gemini-2.0-flash

    programming terms or expressions

    np_token-act-pair-logits · gpt-4o-mini

    code/debugging

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    writeFieldEnd
    -0.92
     שוליים
    -0.90
     BoxFit
    -0.88
    ]")]
    -0.84
     '\\;'
    -0.81
    BeginContext
    -0.80
     unknownFields
    -0.79
     kaynağından
    -0.78
     насељу
    -0.75
    parsedMessage
    -0.75
    POSITIVE LOGITS
     fasse
    0.51
    Sprintf
    0.50
     virke
    0.48
     going
    0.47
     flamme
    0.45
    leggen
    0.44
    verket
    0.43
     <
    0.43
    ><
    0.43
     offers
    0.43
    Act Density 7.868%

    No Known Activations