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
     Connor
    -0.07
    儀
    -0.06
     EO
    -0.06
     면
    -0.06
    sharing
    -0.06
    stim
    -0.06
     пош
    -0.06
    _Ex
    -0.06
     radioButton
    -0.06
    γρα
    -0.06
    POSITIVE LOGITS
     желуд
    0.07
    だって
    0.07
    ิญญ
    0.07
    %',
    0.06
     Kou
    0.06
     AGAIN
    0.06
    _charset
    0.06
    =False
    0.06
    Salir
    0.06
    oubtedly
    0.06
    Act Density 0.140%

    No Known Activations