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

    Neuronpedia

    INDEX
    Explanations

    average

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ！！↵↵
    -0.07
     go
    -0.07
    .Dark
    -0.06
     inout
    -0.06
    ugador
    -0.06
     Clan
    -0.06
    cej
    -0.06
    Entr
    -0.06
     chuyến
    -0.06
    ISE
    -0.06
    POSITIVE LOGITS
    -mean
    0.08
     average
    0.08
    amines
    0.07
     averages
    0.07
     mandate
    0.07
    ські
    0.06
    earning
    0.06
    FAIL
    0.06
    ��
    0.06
     LARGE
    0.06
    Act Density 0.003%

    No Known Activations