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

    Neuronpedia

    INDEX
    Explanations

    online content snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     explaining
    -0.07
    Warning
    -0.07
     diver
    -0.07
     evident
    -0.06
    ��
    -0.06
     thereby
    -0.06
     discussing
    -0.06
     Third
    -0.06
     причины
    -0.06
     Family
    -0.06
    POSITIVE LOGITS
     GetComponent
    0.07
    Tasks
    0.07
    (confirm
    0.06
     boş
    0.06
    {
↵
↵
    0.06
     faux
    0.06
     asian
    0.06
     Amerikan
    0.06
    洗
    0.06
     thematic
    0.06
    Act Density 0.000%

    No Known Activations