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

    Neuronpedia

    INDEX
    Explanations

    indexing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    南通
    -0.08
     dout
    -0.08
    (INPUT
    -0.08
     Barnes
    -0.08
     yPos
    -0.07
     PEOPLE
    -0.07
     MatTable
    -0.07
    Number
    -0.07
     vouchers
    -0.07
    sounds
    -0.07
    POSITIVE LOGITS
    ڧ
    0.07
     espresso
    0.07
    igue
    0.07
    🦐
    0.07
    เฉพ
    0.07
    สะด
    0.07
     initiative
    0.07
    ㈳
    0.07
     ilçe
    0.07
    혜
    0.07
    Act Density 0.007%

    No Known Activations