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

    Neuronpedia

    INDEX
    Explanations

    see

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     श्रेष्ठ
    -0.08
     कथा
    -0.08
    ां
    -0.08
     इच्छा
    -0.08
     भूम
    -0.07
     Bio
    -0.07
     departamentos
    -0.07
     segredo
    -0.07
     Roosevelt
    -0.07
     podcast
    -0.07
    POSITIVE LOGITS
     увидеть
    0.09
    を見る
    0.09
    Observe
    0.09
     Observe
    0.08
    You'll
    0.08
    observe
    0.08
     увид
    0.08
     вклад
    0.08
     появляется
    0.08
     WINDOW
    0.08
    Act Density 0.009%

    No Known Activations