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

    Neuronpedia

    INDEX
    Explanations

    social economic factors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     බොහෝ
    0.49
    union
    0.46
     ermög
    0.44
     करुन
    0.44
    isinde
    0.44
     στον
    0.43
    𐰼
    0.43
    EXAMPLE
    0.42
    ণাস্ত্র
    0.42
    ropoda
    0.42
    POSITIVE LOGITS
     ape
    0.52
     huge
    0.47
     bon
    0.46
     catch
    0.45
     prom
    0.45
     Ape
    0.43
     caricature
    0.43
     eso
    0.42
     ugly
    0.41
     bad
    0.40
    Act Density 0.007%

    No Known Activations