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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating purpose or intent

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

    made to order

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     voisins
    -0.40
     penjara
    -0.40
     saldır
    -0.36
     onun
    -0.33
    udert
    -0.33
     demonios
    -0.32
     libremente
    -0.32
    nictwa
    -0.31
     rumahnya
    -0.31
     comunidade
    -0.31
    POSITIVE LOGITS
    setVerticalGroup
    0.89
    LookAnd
    0.81
     MainAxisSize
    0.79
    complexContent
    0.72
    ArgsConstructor
    0.71
    SequentialGroup
    0.71
     BoxFit
    0.69
    FunctionFlags
    0.68
    WebVitals
    0.66
    webElementXpaths
    0.66
    Act Density 0.020%

    No Known Activations