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

    Neuronpedia

    INDEX
    Explanations

    doi links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    billy
    0.34
     அடித்த
    0.33
     sixteenth
    0.32
     পুষ
    0.32
     Scream
    0.30
    (.
    0.30
     nineteenth
    0.30
    xiii
    0.30
    陇
    0.30
    তাস
    0.30
    POSITIVE LOGITS
     Bethesda
    0.38
     Bois
    0.37
     jer
    0.35
    عتها
    0.35
    安定
    0.35
     મહ
    0.34
     लड़
    0.34
    この記事
    0.34
    عت
    0.33
     Biological
    0.33
    Act Density 0.002%

    No Known Activations