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

    Neuronpedia

    INDEX
    Explanations

    descriptions of actions related to research and web interface interactions

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

    to demonstrate or explain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.43
    RTSC
    -0.40
     kasarigan
    -0.39
    rower
    -0.39
    AISSEE
    -0.39
     esternos
    -0.38
    nze
    -0.37
     للمعارف
    -0.37
    berra
    -0.36
    Personensuche
    -0.36
    POSITIVE LOGITS
     createState
    0.54
     nahilalakip
    0.52
    Życiorys
    0.46
    belea
    0.46
    
    0.41
     trace
    0.41
    HttpPut
    0.40
    utnik
    0.39
    thenReturn
    0.38
    inheritDoc
    0.38
    Act Density 0.177%

    No Known Activations