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

    Neuronpedia

    INDEX
    Explanations

    indicators of progress and improvement

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

    encouraging progress and confidence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nakalista
    -0.79
    IUrlHelper
    -0.68
     disambiguazione
    -0.61
     ब्रेकडाउन
    -0.60
    featureID
    -0.58
     jadx
    -0.57
     ivelany
    -0.54
     gql
    -0.54
    fjspx
    -0.54
     desmotivaciones
    -0.52
    POSITIVE LOGITS
     momentum
    0.43
     confidence
    0.39
     encouraging
    0.38
    Confidence
    0.37
     growth
    0.37
     boost
    0.36
     Confidence
    0.36
     proud
    0.35
     confident
    0.35
    confident
    0.35
    Act Density 0.033%

    No Known Activations