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

    Neuronpedia

    INDEX
    Explanations

    side

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    じゃ
    -0.08
    Instead
    -0.07
    _pose
    -0.07
    olean
    -0.07
    -transfer
    -0.07
     Destructor
    -0.07
    言
    -0.07
     ula
    -0.06
    -su
    -0.06
     بغ
    -0.06
    POSITIVE LOGITS
     Dirty
    0.07
    实惠
    0.07
    浙江大学
    0.07
    .modelo
    0.07
     Gothic
    0.07
    백
    0.07
    х
    0.07
     Ere
    0.07
     Hispan
    0.07
    前锋
    0.06
    Act Density 0.000%

    No Known Activations