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

    Neuronpedia

    INDEX
    Explanations

    length

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scenes
    -0.07
     doubled
    -0.07
     FACE
    -0.07
     announcements
    -0.07
    Officers
    -0.07
     objs
    -0.06
     Sections
    -0.06
    Aud
    -0.06
     lodged
    -0.06
     LW
    -0.06
    POSITIVE LOGITS
    Verified
    0.06
     milfs
    0.06
    uell
    0.06
    Yii
    0.06
    […
    0.06
    官网
    0.06
     čís
    0.06
     forCell
    0.05
    алог
    0.05
    ¯¯
    0.05
    Act Density 0.041%

    No Known Activations