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

    Neuronpedia

    INDEX
    Explanations

    fabric swatches

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tand
    -0.07
    录
    -0.07
    ')↵
    -0.06
    PropertyParams
    -0.06
     tenth
    -0.06
    !");
↵
    -0.06
    ımı
    -0.06
    ?)↵
    -0.06
    #",
    -0.06
    각
    -0.06
    POSITIVE LOGITS
    攻撃
    0.08
     PERMISSION
    0.06
    iguiente
    0.06
     Hatch
    0.06
    ьер
    0.06
     Lag
    0.06
     LEVEL
    0.06
     SERIES
    0.06
     گیاه
    0.06
    XL
    0.06
    Act Density 0.028%

    No Known Activations