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

    Neuronpedia

    INDEX
    Explanations

    public

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     linestyle
    0.56
    Her
    0.55
    asjon
    0.55
     enlaces
    0.54
    Этот
    0.54
    الد
    0.53
     McClellan
    0.53
     StringBuffer
    0.53
     કરતી
    0.53
    惪
    0.53
    POSITIVE LOGITS
     дороже
    0.64
     организаций
    0.63
     পাবলিক
    0.62
     privés
    0.61
     público
    0.59
     públic
    0.58
     publique
    0.58
     Pública
    0.58
     общественных
    0.58
    čko
    0.57
    Act Density 0.000%

    No Known Activations