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

    Neuronpedia

    INDEX
    Explanations

    specific positive descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     badass
    0.94
     dystopian
    0.84
     shitty
    0.82
     YouTuber
    0.76
     collab
    0.74
    🤯
    0.73
     nerdy
    0.71
     tbh
    0.70
    😭
    0.69
     fucked
    0.68
    POSITIVE LOGITS
     healthful
    0.80
     exotic
    0.75
     tropical
    0.66
     antiques
    0.66
     gourmet
    0.66
     unsurpassed
    0.64
     wholesome
    0.63
     deluxe
    0.63
     antique
    0.61
     delectable
    0.61
    Act Density 0.010%

    No Known Activations