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

    Neuronpedia

    INDEX
    Explanations

    Names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    玻璃
    -0.07
    天
    -0.07
     Plot
    -0.06
     bào
    -0.06
     ши
    -0.06
    応
    -0.06
    Jet
    -0.06
     trộn
    -0.06
     ⟨
    -0.06
     ngOn
    -0.06
    POSITIVE LOGITS
    Rose
    0.07
    _expired
    0.06
     realiza
    0.06
    	JSONObject
    0.06
     driven
    0.06
     even
    0.06
     правила
    0.06
    IALIZ
    0.06
    -ranking
    0.06
    にある
    0.06
    Act Density 0.055%

    No Known Activations