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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    0.46
    :
    0.43
    न
    0.37
    aing
    0.36
     LXXX
    0.34
     tasas
    0.34
     honti
    0.34
     ALU
    0.34
     triads
    0.33
     sparsebundle
    0.33
    POSITIVE LOGITS
    ى
    0.55
     have
    0.52
    ين
    0.51
    in
    0.49
    ने
    0.46
    ine
    0.46
     be
    0.43
     to
    0.43
     do
    0.42
    to
    0.42
    Act Density 0.007%

    No Known Activations