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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and appreciation

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

    expressions of thanks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     क्यों
    -0.37
    
    -0.34
     شاید
    -0.34
    RTDA
    -0.34
     đảm
    -0.33
     jabón
    -0.32
    rscheinlich
    -0.32
     fitting
    -0.31
     kanskje
    -0.31
     quoi
    -0.31
    POSITIVE LOGITS
     فريبيس
    0.57
    featureID
    0.55
     ब्रेकडाउन
    0.49
    RTEE
    0.48
     Савезне
    0.48
    WithMany
    0.47
    onenumber
    0.46
     ffilmiau
    0.46
    تفصیلات
    0.45
     Италијани
    0.45
    Act Density 0.008%

    No Known Activations