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

    Neuronpedia

    INDEX
    Explanations

    functional descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Liv
    0.51
    Liv
    0.47
    rica
    0.46
     showdown
    0.46
     Recurs
    0.42
     رياضيات
    0.40
    竞赛
    0.40
     SWAT
    0.39
    फड
    0.39
     STEM
    0.39
    POSITIVE LOGITS
    Seb
    0.38
    anzas
    0.38
    ྲ
    0.38
    雓
    0.37
     allot
    0.37
     причи
    0.36
     especies
    0.36
    Hans
    0.36
     insects
    0.36
    ρας
    0.36
    Act Density 0.000%

    No Known Activations