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

    Neuronpedia

    INDEX
    Explanations

    Rules/Policies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MSE
    -0.07
     наруж
    -0.06
    	Py
    -0.06
     Signup
    -0.06
    ja
    -0.06
    Outside
    -0.06
    (source
    -0.06
    -t
    -0.06
     ql
    -0.06
    :t
    -0.06
    POSITIVE LOGITS
     grind
    0.06
     Hong
    0.06
     ne
    0.06
     Baghd
    0.06
     enriched
    0.06
    合格
    0.06
     integral
    0.06
     галузі
    0.06
    妻
    0.06
    ่วมก
    0.06
    Act Density 0.048%

    No Known Activations