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

    Neuronpedia

    INDEX
    Explanations

    ou

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🥪
    -0.08
     Gravity
    -0.08
    它
    -0.08
    搞
    -0.07
    🎀
    -0.07
     weit
    -0.07
    UNIT
    -0.07
    alance
    -0.07
    .Rows
    -0.07
    〗
    -0.07
    POSITIVE LOGITS
     Mou
    0.08
    OU
    0.07
     youths
    0.07
    �
    0.07
    探访
    0.06
     "./
    0.06
    椐
    0.06
    bilt
    0.06
    ｺ
    0.06
    ϒ
    0.06
    Act Density 0.073%

    No Known Activations