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

    Neuronpedia

    INDEX
    Explanations

    product features and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     homic
    0.62
     heuristics
    0.59
     policymakers
    0.58
     salari
    0.57
     demoral
    0.56
     perverse
    0.56
     perempt
    0.54
     rulemaking
    0.54
     complicating
    0.54
     democracies
    0.53
    POSITIVE LOGITS
    【
    0.95
     Adjustable
    0.89
     Suitable
    0.87
     ，
    0.86
     Convenient
    0.85
     【
    0.84
     DIY
    0.82
    丨
    0.82
     multifunctional
    0.81
     Included
    0.79
    Act Density 0.028%

    No Known Activations