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

    Neuronpedia

    INDEX
    Explanations

    debugging, reproducing errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Afro
    -0.08
    aih
    -0.08
     Raum
    -0.08
    ءَ
    -0.08
    க்கு
    -0.08
    aat
    -0.07
    shwa
    -0.07
    ଶ
    -0.07
    aku
    -0.07
    শ
    -0.07
    POSITIVE LOGITS
     పరిస్థిత
    0.09
     восп
    0.09
     মিল
    0.09
     خورد
    0.08
     ®
    0.08
     reproduce
    0.08
     coax
    0.08
     situações
    0.08
    毛
    0.08
     મળે
    0.08
    Act Density 0.002%

    No Known Activations