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

    Neuronpedia

    INDEX
    Explanations

    DSP

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     coc
    -0.08
     эк
    -0.08
     Ign
    -0.07
     invites
    -0.07
    离去
    -0.07
    ignite
    -0.07
    Return
    -0.07
     Case
    -0.07
     M
    -0.07
     walks
    -0.07
    POSITIVE LOGITS
     chó
    0.08
    ulu
    0.06
    内马尔
    0.06
     inspector
    0.06
    球星
    0.06
     uv
    0.06
     الطب
    0.06
    stud
    0.06
     (↵
    0.06
    좉
    0.06
    Act Density 0.002%

    No Known Activations