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
    Po
    -0.06
     différentes
    -0.06
     gris
    -0.06
    宋体
    -0.06
    -root
    -0.06
    _nv
    -0.06
    "On
    -0.06
     "=
    -0.06
    .Submit
    -0.06
    (IS
    -0.06
    POSITIVE LOGITS
     ビ
    0.07
     Comey
    0.06
     Mens
    0.06
     Truman
    0.06
    イル
    0.06
    @example
    0.06
     حرفه
    0.06
     chứa
    0.06
     西
    0.06
     SB
    0.06
    Act Density 0.014%

    No Known Activations