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

    Neuronpedia

    INDEX
    Explanations

    configuration file

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cycle
    0.50
     Reglamento
    0.49
    ആ
    0.48
     heure
    0.46
    ൫
    0.46
     drawback
    0.46
     Nxg
    0.46
     cependant
    0.46
     Sury
    0.46
     Dlatego
    0.45
    POSITIVE LOGITS
    s
    0.52
    lsen
    0.52
    textcolor
    0.50
    list
    0.50
    li
    0.49
    IMAGES
    0.48
    wchar
    0.46
    ka
    0.46
    ïd
    0.46
    llama
    0.44
    Act Density 0.000%

    No Known Activations