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

    Neuronpedia

    INDEX
    Explanations

    email addresses

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

    email addresses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ligiloj
    -0.70
    rungsseite
    -0.67
     الحره
    -0.61
     poveznice
    -0.60
     للمعارف
    -0.59
     ujednoznacz
    -0.54
     disambiguazione
    -0.52
    astéroïdes
    -0.52
     мәкал
    -0.52
     ModelExpression
    -0.50
    POSITIVE LOGITS
    こちらも
    0.40
     тоже
    0.39
    dropIfExists
    0.39
    Ặ
    0.38
    こちらは
    0.38
     Danke
    0.37
    utivos
    0.37
     similarly
    0.37
    also
    0.36
     pinulongan
    0.36
    Act Density 0.007%

    No Known Activations