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

    Neuronpedia

    INDEX
    Explanations

    chemical structures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     judgments
    -0.08
     posed
    -0.07
    也比较
    -0.07
     automated
    -0.07
    ]},
    -0.07
     GAS
    -0.07
     bakım
    -0.07
    .cache
    -0.07
     muj
    -0.07
     fuera
    -0.07
    POSITIVE LOGITS
    verb
    0.08
     знаю
    0.07
     spokesperson
    0.06
    槍
    0.06
    مصلحة
    0.06
     ליצור
    0.06
     regex
    0.06
    員
    0.06
     peux
    0.06
     להמשיך
    0.06
    Act Density 0.005%

    No Known Activations