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

    Neuronpedia

    INDEX
    Explanations

    code/errors/apologies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ='/
    -0.07
    -io
    -0.07
    Brand
    -0.07
    舍不得
    -0.07
    ="../
    -0.07
    POINT
    -0.07
    brand
    -0.07
    .hit
    -0.07
    AME
    -0.07
     Service
    -0.07
    POSITIVE LOGITS
    .a
    0.07
    ilihan
    0.07
     refers
    0.07
     invariant
    0.07
    (words
    0.07
    媳
    0.06
     Cynthia
    0.06
     pav
    0.06
     hal
    0.06
    ꦭ
    0.06
    Act Density 0.071%

    No Known Activations