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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    輪
    -0.08
     kỳ
    -0.07
    ambio
    -0.07
     drafts
    -0.06
    _pull
    -0.06
    ши
    -0.06
    服
    -0.06
    ить
    -0.06
    acija
    -0.06
     pants
    -0.06
    POSITIVE LOGITS
     velké
    0.07
    CurrentUser
    0.07
    [h
    0.06
     Showing
    0.06
     resc
    0.06
    loff
    0.06
    ใส
    0.06
    incy
    0.06
    hall
    0.06
    _def
    0.06
    Act Density 0.223%

    No Known Activations