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

    Neuronpedia

    INDEX
    Explanations

    bibliographic entries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ing
    0.50
     vasta
    0.46
     deva
    0.46
     raio
    0.46
    -
    0.46
     arti
    0.44
    فو
    0.43
    /
    0.43
     territoire
    0.43
     territory
    0.42
    POSITIVE LOGITS
     Од
    0.52
     ម
    0.51
    ብስ
    0.50
    ład
    0.50
    łąd
    0.48
    그램
    0.47
    śred
    0.47
    ských
    0.47
    ęb
    0.47
    लम
    0.47
    Act Density 0.000%

    No Known Activations