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

    Neuronpedia

    INDEX
    Explanations

    two, operands, or indices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    भावना
    0.66
     어려
    0.66
     scandals
    0.66
    HTTPS
    0.65
    httphttps
    0.65
    보다는
    0.65
    beat
    0.64
     이유
    0.64
    充実
    0.64
     Cashback
    0.63
    POSITIVE LOGITS
     vertices
    0.77
     дві
    0.75
     operands
    0.75
     dois
    0.73
     two
    0.72
    そして
    0.71
     กับ
    0.70
    和一个
    0.69
     Two
    0.68
     Kedua
    0.68
    Act Density 0.004%

    No Known Activations