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

    Neuronpedia

    INDEX
    Explanations

    server listening logs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ленных
    0.47
    нала
    0.46
    籮
    0.45
    ленные
    0.44
    бели
    0.44
    iencia
    0.44
    στή
    0.42
    బె
    0.42
     parishioners
    0.42
    ﹁
    0.42
    POSITIVE LOGITS
    z
    0.52
    tissue
    0.51
     پڑھیئے
    0.44
    sized
    0.42
    assessment
    0.42
    t
    0.41
    8
    0.41
    ティ
    0.40
    ice
    0.40
    Tissue
    0.40
    Act Density 0.003%

    No Known Activations