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

    Neuronpedia

    INDEX
    Explanations

    explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     namesake
    0.79
     classified
    0.77
     eponymous
    0.73
     nucleation
    0.71
     subroutine
    0.71
     bidirectional
    0.70
     foreseeable
    0.70
     placebo
    0.68
     honorary
    0.68
     affirmative
    0.68
    POSITIVE LOGITS
    Explanation
    0.97
     Explanation
    0.80
    Copy
    0.80
    css
    0.79
    Explain
    0.77
    Вы
    0.77
    lead
    0.75
    explain
    0.75
    This
    0.74
    Song
    0.73
    Act Density 0.172%

    No Known Activations