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

    Neuronpedia

    INDEX
    Explanations

    cross followed by specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     across
    0.46
    across
    0.45
    Across
    0.43
     separados
    0.43
    Transaksi
    0.42
     कन्व
    0.40
     separado
    0.39
     Across
    0.38
    earth
    0.37
    passed
    0.37
    POSITIVE LOGITS
     Cross
    0.63
     ক্রস
    0.59
     cross
    0.57
    cross
    0.52
    Cross
    0.51
     Cro
    0.51
     CROSS
    0.51
     क्रॉस
    0.50
     Cros
    0.49
     CRO
    0.49
    Act Density 0.007%

    No Known Activations