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

    Neuronpedia

    INDEX
    Explanations

    bullet points and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Dix
    0.66
    hasOwnProperty
    0.64
    merksamkeit
    0.62
    strtolower
    0.62
    $
    0.61
    \"
    0.61
    Longueur
    0.60
    attendance
    0.60
    loved
    0.59
    occur
    0.58
    POSITIVE LOGITS
    1.37
     ·
    1.28
     ・
    1.26
       
    1.23
     •
    1.22
         
    1.14
     ●
    1.09
     ->
    1.08
        
    1.07
    1.06
    Act Density 0.147%

    No Known Activations