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

    Neuronpedia

    INDEX
    Explanations

    HTML tag <hr

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ת
    -0.08
    (input
    -0.08
    		  ↵
    -0.07
    javascript
    -0.07
     title
    -0.07
    _start
    -0.07
     Armen
    -0.07
     TC
    -0.07
     overlay
    -0.07
    _ON
    -0.06
    POSITIVE LOGITS
    _MISS
    0.08
     хроничес
    0.07
     کشورهای
    0.06
     Sevent
    0.06
     Evropské
    0.06
    .CurrentRow
    0.06
    navbarSupportedContent
    0.06
    งเศ
    0.06
     соч
    0.06
     وقتی
    0.06
    Act Density 0.002%

    No Known Activations