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

    Neuronpedia

    INDEX
    Explanations

    clichés and common tropes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Unix
    0.45
    Linux
    0.44
     disobedience
    0.42
     लाहि
    0.42
    Planck
    0.41
     beautifully
    0.41
    philosoph
    0.41
    พาะ
    0.40
     Witcher
    0.39
     क्रांतिकारी
    0.39
    POSITIVE LOGITS
     clichés
    0.91
     cheesy
    0.84
     tacky
    0.75
     cliché
    0.75
     stereotypical
    0.73
     cliche
    0.70
     sacchar
    0.66
     ubiquitous
    0.66
     suburban
    0.65
     faux
    0.63
    Act Density 0.248%

    No Known Activations