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

    Neuronpedia

    INDEX
    Explanations

    Legal citations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     çoğu
    -0.08
    �
    -0.07
    �
    -0.07
    encv
    -0.07
    pired
    -0.07
    apper
    -0.07
    =size
    -0.07
    醒来
    -0.07
     pulp
    -0.07
     المعارضة
    -0.07
    POSITIVE LOGITS
    Hierarchy
    0.07
    დ
    0.07
    闭
    0.07
     S
    0.06
    xp
    0.06
    𝒌
    0.06
    isRequired
    0.06
    nivel
    0.06
     אודות
    0.06
    гон
    0.06
    Act Density 0.001%

    No Known Activations