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

    Neuronpedia

    INDEX
    Explanations

    negative numbers and their associations

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

    Tokens before or after dates

    np_acts-logits-general · gemini-2.0-flash

    dates or times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CURIAM
    -0.75
    InputBorder
    -0.74
     ligiloj
    -0.69
    GraphicsUnit
    -0.69
    Życiorys
    -0.63
     EClass
    -0.62
    omitempty
    -0.59
    Portale
    -0.59
    setupUi
    -0.59
     BoxDecoration
    -0.58
    POSITIVE LOGITS
    0
    0.64
    1
    0.59
     dreht
    0.49
    ForValue
    0.42
    нциклопе
    0.42
    2
    0.41
     hereto
    0.41
    toLowerCase
    0.40
     conmigo
    0.40
     kuni
    0.40
    Act Density 0.237%

    No Known Activations