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

    Neuronpedia

    INDEX
    Explanations

    $ amounts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    haviours
    1.11
     contato
    1.00
     mềm
    1.00
     guaranty
    0.99
    ými
    0.99
    为一个
    0.98
    okość
    0.97
     Sistemi
    0.97
     creeks
    0.96
    enegro
    0.96
    POSITIVE LOGITS
    er
    1.04
     Journalist
    1.00
    ค
    0.99
     ganske
    0.94
    ர்
    0.92
     supposing
    0.92
    𝐧
    0.91
    erweise
    0.91
    र
    0.91
    Veter
    0.91
    Act Density 0.002%

    No Known Activations