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

    Neuronpedia

    INDEX
    Explanations

    terms and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     빠르게
    0.91
     목표
    0.89
     지역
    0.82
     checksum
    0.78
     konserv
    0.78
     langfrist
    0.75
     Wszyst
    0.73
     건강
    0.72
     asesin
    0.72
     항목
    0.72
    POSITIVE LOGITS
     parties
    1.13
     notice
    1.01
     breach
    0.91
     remedies
    0.91
    parties
    0.87
     Parties
    0.84
     पार्टियों
    0.84
     notices
    0.83
     party
    0.81
     contemplated
    0.81
    Act Density 0.312%

    No Known Activations