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

    Neuronpedia

    INDEX
    Explanations

    there's no single best

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bazı
    0.56
     ciertas
    0.55
     gewisse
    0.55
     certains
    0.54
     существуют
    0.53
     certaines
    0.53
     bestimmten
    0.52
     situations
    0.51
     ചില
    0.51
     ciertos
    0.51
    POSITIVE LOGITS
     vibrancy
    0.43
     जमकर
    0.42
     Poc
    0.38
    大量
    0.38
    endip
    0.37
    iet
    0.37
    ='\
    0.37
     Weddings
    0.37
    cer
    0.37
     Boud
    0.36
    Act Density 0.001%

    No Known Activations