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

    Neuronpedia

    INDEX
    Explanations

    Base64 encoding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.21
    ;
    0.18
    first
    0.16
    ᥙ
    0.16
     half
    0.15
     ス
    0.15
    icon
    0.15
     magnific
    0.15
     pearl
    0.15
     Mathematics
    0.15
    POSITIVE LOGITS
     enjeux
    0.18
     débat
    0.18
    Webhook
    0.18
     সচেতন
    0.18
     incentiv
    0.17
    GTBase
    0.17
     SaaS
    0.17
     omnichannel
    0.17
     onboarding
    0.17
     ఉపయోగ
    0.17
    Act Density 0.013%

    No Known Activations