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

    Neuronpedia

    INDEX
    Explanations

    code or technical references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iez
    -0.07
    _On
    -0.07
    añ
    -0.07
     Mountains
    -0.07
    otros
    -0.07
    -scalable
    -0.07
     sham
    -0.07
    нка
    -0.07
    itan
    -0.06
    seo
    -0.06
    POSITIVE LOGITS
     „
    0.06
     herkes
    0.06
    	field
    0.06
     George
    0.06
     стад
    0.06
    工
    0.06
     돈
    0.06
    .dtp
    0.06
    カテゴリ
    0.06
    	state
    0.05
    Act Density 0.000%

    No Known Activations