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

    Neuronpedia

    INDEX
    Explanations

    Site

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ếc
    -0.07
    梅
    -0.07
    Chinese
    -0.07
    implicitly
    -0.07
    んですけど
    -0.06
    Per
    -0.06
    占有
    -0.06
    ไหน
    -0.06
    颠
    -0.06
    pliant
    -0.06
    POSITIVE LOGITS
     التش
    0.07
     STORE
    0.07
     bas
    0.07
    党风廉政
    0.07
     flav
    0.06
     aujourd
    0.06
    شاش
    0.06
     fChain
    0.06
    ᗗ
    0.06
    _rad
    0.06
    Act Density 0.037%

    No Known Activations