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

    Neuronpedia

    INDEX
    Explanations

    ormal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tad
    -0.07
     phantom
    -0.07
     gia
    -0.07
    Carl
    -0.07
    혈
    -0.06
     avanz
    -0.06
     cambiar
    -0.06
    曹
    -0.06
    趋
    -0.06
    _sup
    -0.06
    POSITIVE LOGITS
    周恩来
    0.07
    梾
    0.07
    옻
    0.07
    ᆼ
    0.07
     presses
    0.06
     shrine
    0.06
     lazım
    0.06
    网址
    0.06
    ज
    0.06
    𝕺
    0.06
    Act Density 0.001%

    No Known Activations