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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "on" and its various contexts in a document

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

    coming on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UObject
    -0.43
    HomeAsUp
    -0.43
    -0.42
    yentes
    -0.38
     fabricant
    -0.37
    だ
    -0.37
     utilizando
    -0.36
     åt
    -0.36
    limsy
    -0.36
    gevens
    -0.35
    POSITIVE LOGITS
    RegressionTest
    0.60
     queſta
    0.59
    TagMode
    0.55
    pecabe
    0.52
    SBATCH
    0.52
    AddTagHelper
    0.52
    principalColumn
    0.52
    Slf
    0.51
     oncoming
    0.51
     bandou
    0.50
    Act Density 0.006%

    No Known Activations