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

    Neuronpedia

    INDEX
    Explanations

    4

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    颡
    -0.08
    还算
    -0.08
    令人
    -0.07
     guy
    -0.07
     ese
    -0.07
     الجو
    -0.07
     welcoming
    -0.07
     Ministry
    -0.07
    bufio
    -0.07
    Native
    -0.07
    POSITIVE LOGITS
    информ
    0.08
     kost
    0.07
    *>(
    0.07
    before
    0.07
     POLL
    0.07
    iffin
    0.07
     Passing
    0.07
    Ⓣ
    0.06
     genitals
    0.06
    牟
    0.06
    Act Density 0.004%

    No Known Activations