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

    Neuronpedia

    INDEX
    Explanations

    foreign languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     congressman
    -0.07
    考えて
    -0.07
     disappointing
    -0.07
    出院
    -0.06
    [at
    -0.06
     PLACE
    -0.06
    (Spring
    -0.06
    .WRITE
    -0.06
    !<
    -0.06
    ườ
    -0.06
    POSITIVE LOGITS
    哺
    0.07
    挡
    0.07
    ^^
    0.07
     principalColumn
    0.07
    その後
    0.07
    ^^^^
    0.07
    �자
    0.07
     ----------
    0.07
     varios
    0.07
    嫂
    0.07
    Act Density 0.002%

    No Known Activations