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

    Neuronpedia

    INDEX
    Explanations

    duality and resolving issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ch
    0.45
    village
    0.44
     Hasta
    0.43
    rib
    0.42
     captcha
    0.42
    LW
    0.41
     aug
    0.40
    rewrite
    0.40
    nov
    0.40
    elekt
    0.40
    POSITIVE LOGITS
    বোন
    0.46
     PDEs
    0.42
    ждений
    0.42
    颉
    0.41
     Flags
    0.41
    Pairs
    0.40
    atov
    0.40
     свя
    0.40
    יות
    0.39
     Polaribacter
    0.39
    Act Density 0.000%

    No Known Activations