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

    Neuronpedia

    INDEX
    Explanations

    numerical values and mathematical expressions

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

    multiple choice answers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    onAttach
    -0.47
    XtraReports
    -0.44
    oriam
    -0.43
     CFC
    -0.43
     CTA
    -0.43
     PTC
    -0.43
     GTI
    -0.42
     Sb
    -0.42
     Wix
    -0.42
    raborty
    -0.42
    POSITIVE LOGITS
     étoient
    0.47
     Réponses
    0.46
    Tikang
    0.43
     betweenstory
    0.42
     ciudadana
    0.39
     przedmio
    0.39
    0.39
     tertulis
    0.39
     veuillez
    0.38
     colgantes
    0.38
    Act Density 0.002%

    No Known Activations