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

    Neuronpedia

    INDEX
    Explanations

    foreign language symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Piot
    0.51
     associating
    0.50
     Prz
    0.50
     nella
    0.47
     fian
    0.47
     C
    0.47
     financ
    0.47
     biometric
    0.46
     Seda
    0.45
     Weg
    0.45
    POSITIVE LOGITS
    LLCATS
    0.56
     तात्
    0.51
     нарушение
    0.51
     විශේෂ
    0.50
    кс
    0.49
    сс
    0.49
     рабочий
    0.49
     कष्ट
    0.47
     అవకాశం
    0.46
     جای
    0.46
    Act Density 0.003%

    No Known Activations