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

    Neuronpedia

    INDEX
    Explanations

    reasonable requirements to consent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     হজ
    0.94
     Decimal
    0.90
     Resilience
    0.87
     請
    0.83
    োনায়
    0.80
    갇
    0.79
     rozgry
    0.78
     resilience
    0.76
     Complimentary
    0.76
     빠르게
    0.76
    POSITIVE LOGITS
     reasonably
    1.62
     reasonable
    1.52
    reasonably
    1.37
    reasonable
    1.34
     reasonableness
    1.26
     unreasonably
    1.22
     unreasonable
    1.19
     Reasonable
    1.19
     affirmatively
    1.19
     foreseeable
    1.15
    Act Density 0.328%

    No Known Activations