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

    Neuronpedia

    INDEX
    Explanations

    statement and code syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    frameN
    0.44
    block
    0.42
    ANGE
    0.42
    enge
    0.42
     Gunners
    0.42
    min
    0.42
    DIRECTORY
    0.42
    뱀
    0.41
     Archaeology
    0.41
     Dae
    0.41
    POSITIVE LOGITS
     atribu
    0.53
     mocked
    0.52
     esimerk
    0.51
     khẳng
    0.47
     exemplo
    0.47
     desempen
    0.46
     mostrou
    0.46
     país
    0.46
     captivated
    0.45
    伌
    0.45
    Act Density 0.000%

    No Known Activations