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

    Neuronpedia

    INDEX
    Explanations

    centripetal force

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vou
    -0.07
     cocks
    -0.07
    _TXT
    -0.07
    .emplace
    -0.06
    另有
    -0.06
    ᐖ
    -0.06
    御
    -0.06
    �
    -0.06
    _reset
    -0.06
    卮
    -0.06
    POSITIVE LOGITS
     fluent
    0.08
    на
    0.07
    	renderer
    0.07
    appear
    0.07
    кли
    0.07
    kea
    0.07
    高效
    0.07
    نهار
    0.07
    głos
    0.07
     Brill
    0.07
    Act Density 0.008%

    No Known Activations