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

    Neuronpedia

    INDEX
    Explanations

    parliamentary debate

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    差点
    -0.07
    暴雨
    -0.07
     RAF
    -0.07
    蹚
    -0.06
    (".",
    -0.06
    เต
    -0.06
     בהם
    -0.06
     louder
    -0.06
    溅
    -0.06
    啸
    -0.06
    POSITIVE LOGITS
    ↵     ↵
    0.09
    -shell
    0.08
     состоит
    0.08
     Lock
    0.07
     homo
    0.07
    UGIN
    0.07
    Conversation
    0.07
    acam
    0.06
     observation
    0.06
    绝缘
    0.06
    Act Density 0.000%

    No Known Activations