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

    Neuronpedia

    INDEX
    Explanations

    terms and conditions clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     드러
    0.98
     제도
    0.87
     realtà
    0.83
    établ
    0.81
     만들기
    0.78
     ஆதார
    0.78
     रीट
    0.76
    bigoplus
    0.76
     수요
    0.75
     réalité
    0.74
    POSITIVE LOGITS
     termination
    1.43
     Termination
    1.37
    Termination
    1.34
     clause
    1.19
     agrees
    1.17
    termination
    1.11
     clauses
    1.11
     Terms
    1.11
    Term
    1.10
     indemnify
    1.10
    Act Density 0.163%

    No Known Activations