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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SECTION
    -0.06
    ^{
    -0.06
    辦
    -0.06
     leur
    -0.06
     Myers
    -0.06
     Heck
    -0.06
    _buf
    -0.06
     dct
    -0.06
     FIR
    -0.06
    :@
    -0.06
    POSITIVE LOGITS
     accessToken
    0.07
    Consum
    0.07
     cj
    0.06
    components
    0.06
    规划
    0.06
    ุรก
    0.06
     approx
    0.06
    part
    0.06
    ingly
    0.06
    提高
    0.06
    Act Density 0.011%

    No Known Activations