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

    Neuronpedia

    INDEX
    Explanations

    a [noun]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ihe
    1.23
     HIS
    1.20
     some
    1.19
    )<
    1.15
     alcuni
    1.14
     kaikki
    1.14
     an
    1.13
     некоторое
    1.11
     plenty
    1.06
     kyll
    1.06
    POSITIVE LOGITS
    躁
    1.06
    ancy
    1.02
    vorm
    1.02
    佻
    1.00
    Existe
    0.99
     നമ്പർ
    0.99
    of
    0.98
     味
    0.96
    й
    0.96
    ético
    0.95
    Act Density 0.145%

    No Known Activations