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

    Neuronpedia

    INDEX
    Explanations

    closing brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ัจจ
    -0.06
     разі
    -0.06
     دور
    -0.06
    øj
    -0.06
     Gaussian
    -0.06
    LocalizedString
    -0.06
     平方
    -0.06
     국제
    -0.06
     перс
    -0.06
    delivery
    -0.06
    POSITIVE LOGITS
    ]
    0.08
     WD
    0.07
     Flyers
    0.07
    _BUF
    0.07
    rics
    0.07
    >/<
    0.07
    .titleLabel
    0.06
     ―
    0.06
    :UI
    0.06
    �
    0.06
    Act Density 0.005%

    No Known Activations