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

    Neuronpedia

    INDEX
    Explanations

    punctuation and symbols that indicate speech or questions

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

    output followed by Array

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     OFDb
    -0.47
    ViewFeatures
    -0.46
    الإنجليزية
    -0.41
    Filmografie
    -0.39
     OMITBAD
    -0.38
    InitVars
    -0.38
     breathed
    -0.37
    webElementXpaths
    -0.37
    CrossRef
    -0.37
     freed
    -0.37
    POSITIVE LOGITS
     Output
    0.57
     output
    0.56
     OUTPUT
    0.50
    Salida
    0.50
    output
    0.50
    输出
    0.49
    Output
    0.49
     outputs
    0.48
    OUTPUT
    0.46
    Let
    0.44
    Act Density 0.006%

    No Known Activations