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

    Neuronpedia

    INDEX
    Explanations

    Kemal Kılıçdaroğlu

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AssignableFrom
    0.47
     שלה
    0.46
    ঘ্র
    0.46
    ይታ
    0.46
    before
    0.45
    baseline
    0.45
    factors
    0.45
     કર્મચારી
    0.44
     теат
    0.44
    因子
    0.43
    POSITIVE LOGITS
     sieben
    0.47
     möchten
    0.44
     sechs
    0.43
     häufig
    0.42
     tareas
    0.42
     aucun
    0.42
     einer
    0.41
     actividades
    0.41
     Angels
    0.41
     endlich
    0.41
    Act Density 0.002%

    No Known Activations