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

    Neuronpedia

    INDEX
    Explanations

    dialogue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Recommend
    -0.08
    istance
    -0.08
    uzzy
    -0.08
    _bucket
    -0.08
    遗产
    -0.08
    滾
    -0.07
    ，请
    -0.07
    B
    -0.07
    摇头
    -0.07
    七
    -0.07
    POSITIVE LOGITS
     dialogue
    0.08
    〶
    0.07
    _portal
    0.07
     and
    0.07
    洙
    0.07
     Barth
    0.07
    noopener
    0.07
    .beginPath
    0.07
     знак
    0.07
    	matrix
    0.07
    Act Density 0.011%

    No Known Activations