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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    根据
    -0.07
    vised
    -0.07
     FIXED
    -0.07
    市场
    -0.06
     نظام
    -0.06
     Ost
    -0.06
    овари
    -0.06
    ’un
    -0.06
    оци
    -0.06
    appear
    -0.06
    POSITIVE LOGITS
     �
    0.07
    _interface
    0.07
     заг
    0.07
    (arg
    0.07
    (per
    0.07
    .builder
    0.06
    —even
    0.06
     caval
    0.06
    replaceAll
    0.06
    \Message
    0.06
    Act Density 0.025%

    No Known Activations