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

    Neuronpedia

    INDEX
    Explanations

    references to events or actions relating to a database or system processes

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

    Code or markup snippets

    np_acts-logits-general · gemini-2.0-flash

    going to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     发表于
    -0.47
     Cross
    -0.45
     Sweet
    -0.44
    Facades
    -0.44
     interni
    -0.42
     Inter
    -0.42
     Ka
    -0.41
    呢
    -0.41
    ulosa
    -0.41
    inter
    -0.39
    POSITIVE LOGITS
    ंदीखरीदारी
    0.87
    SourceChecksum
    0.87
    تقاوى
    0.86
    enumii
    0.81
     CreateTagHelper
    0.81
    ⓧ
    0.81
     المعرف
    0.79
     myſelf
    0.78
     ModelExpression
    0.78
     >=",
    0.76
    Act Density 0.098%

    No Known Activations