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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Drink
    -0.07
     ход
    -0.07
    -l
    -0.06
    Suc
    -0.06
    icap
    -0.06
    Tester
    -0.06
     Socialist
    -0.06
     ADM
    -0.06
     Squadron
    -0.06
    Containing
    -0.06
    POSITIVE LOGITS
    ————
    0.06
     дальней
    0.06
    ograf
    0.06
     речі
    0.06
     Refriger
    0.06
    .Man
    0.06
     ]);↵
    0.06
     ---------
    0.06
     teste
    0.06
    verige
    0.06
    Act Density 0.032%

    No Known Activations