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

    Neuronpedia

    INDEX
    Explanations

    references to research studies and findings

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

    introducing additional findings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -0.35
     betweenstory
    -0.34
    Definition
    -0.33
     cuir
    -0.33
     dozens
    -0.32
     suyo
    -0.32
    PT
    -0.32
     how
    -0.32
    qrst
    -0.31
    idão
    -0.31
    POSITIVE LOGITS
    rungsseite
    0.63
    0.63
     חיצוניים
    0.59
     يتيمه
    0.59
    endforeach
    0.58
    évaluateur
    0.58
     snippetHide
    0.56
    also
    0.56
    writeFieldEnd
    0.55
     también
    0.54
    Act Density 0.102%

    No Known Activations