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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases regarding the appropriateness or suitability of choices

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

    if evaluating options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    esModule
    -0.50
     preghiera
    -0.49
     iprot
    -0.48
     doPost
    -0.46
    jsonwebtoken
    -0.42
    withOpacity
    -0.41
     hjär
    -0.41
    μως
    -0.40
    KommentareTeilen
    -0.40
    MessageTagHelper
    -0.40
    POSITIVE LOGITS
    rawDesc
    0.43
     Fils
    0.39
    AndEndTag
    0.38
     мәкал
    0.36
     ExecuteAsync
    0.35
     tindak
    0.35
     ***!
    0.34
     finanzi
    0.33
     GenerationType
    0.33
    assas
    0.33
    Act Density 0.071%

    No Known Activations