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

    Neuronpedia

    INDEX
    Explanations

    apostrophe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SPDX
    -0.07
     Hôm
    -0.07
     Vivo
    -0.06
    阶层
    -0.06
    גב
    -0.06
    /User
    -0.06
    خضر
    -0.06
     beğ
    -0.06
     FO
    -0.06
    (ld
    -0.06
    POSITIVE LOGITS
    epar
    0.07
     FOUND
    0.07
     McKin
    0.07
    ()),
    0.07
    윗
    0.07
    克拉
    0.07
     Chall
    0.07
    чист
    0.07
    Waiting
    0.07
    azar
    0.07
    Act Density 0.003%

    No Known Activations