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

    Neuronpedia

    INDEX
    Explanations

    scary stories, fictional pregnant, dictionary definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     problemi
    0.57
    писа
    0.50
     ruolo
    0.50
     piccoli
    0.49
     uomini
    0.49
     dott
    0.49
     splashed
    0.48
     prossimo
    0.47
     titoli
    0.47
     ricerca
    0.46
    POSITIVE LOGITS
    allic
    0.57
    era
    0.53
    onders
    0.52
    ware
    0.50
    ering
    0.50
    ener
    0.46
    aker
    0.45
    enger
    0.45
    /"
    0.45
     लागत
    0.45
    Act Density 0.000%

    No Known Activations