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

    Neuronpedia

    INDEX
    Explanations

    AI capabilities and limitations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ovski
    0.49
    ଫ
    0.48
     Snapchat
    0.45
     Fintech
    0.45
     cybersecurity
    0.44
     desist
    0.44
     TikTok
    0.44
     sécur
    0.44
     dacă
    0.43
     consentement
    0.43
    POSITIVE LOGITS
     enormous
    0.50
     immense
    0.48
     jährlich
    0.47
     myriad
    0.45
    ０
    0.45
    ritic
    0.43
     macroscopic
    0.43
    EOL
    0.42
     огром
    0.42
     ಗಾ
    0.42
    Act Density 0.022%

    No Known Activations