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

    Neuronpedia

    INDEX
    Explanations

    scale

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    奶
    -0.07
    lus
    -0.07
    𝐃
    -0.07
    עם
    -0.07
    ניס
    -0.07
    education
    -0.06
     ngủ
    -0.06
    idor
    -0.06
    יח
    -0.06
    谏
    -0.06
    POSITIVE LOGITS
    .lang
    0.07
    三方
    0.07
     Magento
    0.07
    双创
    0.07
     Bose
    0.07
    conda
    0.07
    -body
    0.07
     PowerShell
    0.06
     /.
    0.06
     vanished
    0.06
    Act Density 0.001%

    No Known Activations