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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing positive experiences or feelings

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

    expressing thanks or positive sentiment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rå
    -0.36
     Diagnose
    -0.35
     negativas
    -0.35
     Gewichts
    -0.35
     larges
    -0.34
     ขาว
    -0.34
     Norvège
    -0.34
     terciopelo
    -0.33
     situation
    -0.32
     australiano
    -0.32
    POSITIVE LOGITS
    printStackTrace
    0.62
    szönöm
    0.61
    findpost
    0.52
    CompleteListener
    0.52
    GRACIAS
    0.50
    楽しかった
    0.49
    ItemBackground
    0.49
     betweenstory
    0.49
    featureID
    0.48
    WebVitals
    0.48
    Act Density 0.028%

    No Known Activations