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

    Neuronpedia

    INDEX
    Explanations

    mathematical operations and calculations

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

    Negative numbers or arithmetic operations

    np_acts-logits-general · gemini-2.0-flash

    negative numbers or hyphen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.54
    SerializedName
    -0.53
    AddHtmlAttribute
    -0.52
    .***
    -0.52
    agisse
    -0.51
    脚注の使い方
    -0.51
     通販
    -0.49
    ման
    -0.48
    ğraf
    -0.48
    rrggbb
    -0.47
    POSITIVE LOGITS
     −
    1.68
     $-
    1.61
     -
    1.61
    −
    1.37
     $-\
    1.35
     }-
    1.26
     negative
    1.25
    －
    1.23
     "-
    1.23
     –
    1.21
    Act Density 1.406%

    No Known Activations