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

    Neuronpedia

    INDEX
    Explanations

    consent, comfort, objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಗೋ
    0.55
    юць
    0.48
    Ꮰ
    0.48
    יה
    0.47
    𝙪
    0.47
    ciende
    0.46
     erh
    0.45
     ਨਹੀਂ
    0.45
     כבר
    0.45
     ד
    0.45
    POSITIVE LOGITS
     Disney
    0.49
     plenary
    0.45
     consent
    0.44
     session
    0.41
    ,
    0.41
     Recap
    0.41
     Batman
    0.40
     Bishop
    0.39
     unintentionally
    0.39
     amended
    0.39
    Act Density 0.004%

    No Known Activations