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

    Neuronpedia

    INDEX
    Explanations

    quantities, degrees, or sequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ClFN
    0.80
     reimag
    0.79
     महज
    0.74
    珬
    0.71
    溘
    0.71
    ग़
    0.70
    Благо
    0.68
    䇝
    0.68
    <unused273>
    0.67
    Alternatively
    0.67
    POSITIVE LOGITS
     muitos
    0.97
     many
    0.96
     meget
    0.96
     muito
    0.93
    มาก
    0.93
     very
    0.92
     veel
    0.91
     molto
    0.91
     mycket
    0.91
     yes
    0.89
    Act Density 0.094%

    No Known Activations