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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     нет
    -0.07
    엜
    -0.07
    -0.07
     mondo
    -0.07
    дается
    -0.07
     das
    -0.07
    die
    -0.07
    糖
    -0.06
    connection
    -0.06
     nuovo
    -0.06
    POSITIVE LOGITS
    ﯿ
    0.08
     Registr
    0.08
    🦈
    0.08
    مفه
    0.07
     bright
    0.07
    ござ
    0.07
    PageRoute
    0.07
    ﯾ
    0.07
     objectMapper
    0.07
    וצא
    0.07
    Act Density 0.036%

    No Known Activations