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

    Neuronpedia

    INDEX
    Explanations

    asterisk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    馓
    -0.08
    穑
    -0.07
    مد
    -0.07
    片面
    -0.06
    _Des
    -0.06
    蓐
    -0.06
     Cold
    -0.06
     veterin
    -0.06
     şiddet
    -0.06
     Veranst
    -0.06
    POSITIVE LOGITS
    LOOP
    0.07
    ips
    0.06
    っていた
    0.06
    mutation
    0.06
    ighbours
    0.06
    כתיבה
    0.06
    _refresh
    0.06
    ographics
    0.06
    发展的
    0.06
     ↵
    0.06
    Act Density 0.001%

    No Known Activations