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

    Neuronpedia

    INDEX
    Explanations

    judging necessity or appropriateness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     positive
    0.77
     positiv
    0.76
    കൃ
    0.74
     варто
    0.74
    positive
    0.73
     positively
    0.72
     Positive
    0.72
    Positive
    0.71
     positivas
    0.71
     सकारात्मक
    0.71
    POSITIVE LOGITS
     convenience
    1.19
    Conven
    1.13
     convenient
    1.07
    conven
    1.07
     Convenience
    1.02
     Convenient
    0.99
     politic
    0.89
     expediency
    0.88
     Advis
    0.88
     удоб
    0.86
    Act Density 0.006%

    No Known Activations