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

    Neuronpedia

    INDEX
    Explanations

    Punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     incel
    -0.07
    จะม
    -0.07
    .Rendering
    -0.07
     coaster
    -0.06
    
    -0.06
     эффек
    -0.06
     ประเทศ
    -0.06
    衣
    -0.06
    raně
    -0.06
     Indones
    -0.06
    POSITIVE LOGITS
     IPCC
    0.07
    MESSAGE
    0.06
     models
    0.06
    *****/↵
    0.06
     macro
    0.06
     adc
    0.06
    .Property
    0.06
    getPost
    0.06
    波
    0.06
     mysterious
    0.06
    Act Density 0.027%

    No Known Activations