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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "to be" and their associated contexts

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

    people are doing things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itself
    -0.45
     avantages
    -0.37
     exigences
    -0.36
    ยาว
    -0.36
    を行う
    -0.34
    itself
    -0.32
     cielos
    -0.32
    単
    -0.32
    rzez
    -0.32
     Gründ
    -0.32
    POSITIVE LOGITS
     intptr
    0.74
    errHandler
    0.74
    webElementXpaths
    0.71
     onOptions
    0.70
     ujednoznacz
    0.66
    setVerticalGroup
    0.65
     referenties
    0.64
    yntaxException
    0.64
    parsedMessage
    0.64
    JspWriter
    0.63
    Act Density 0.045%

    No Known Activations