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

    Neuronpedia

    INDEX
    Explanations

    surfaces and outer layers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ۔
    0.46
     தொழில்நுட்ப
    0.46
    któ
    0.43
    .
    0.41
    überküloz
    0.40
     உருவாக்க
    0.40
     போன்றவற்ற
    0.39
    ipers
    0.38
    ornos
    0.38
    łym
    0.38
    POSITIVE LOGITS
    ad
    0.47
     of
    0.44
    E
    0.44
    an
    0.43
    A
    0.42
    ان
    0.41
    0.39
     be
    0.39
    า
    0.38
    ח
    0.38
    Act Density 0.227%

    No Known Activations