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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Enc
    -0.07
    perhaps
    -0.07
     glaring
    -0.07
    рож
    -0.07
     computation
    -0.07
     biggest
    -0.06
     Projectile
    -0.06
     fazla
    -0.06
     особ
    -0.06
     khuẩn
    -0.06
    POSITIVE LOGITS
     pubs
    0.07
    tero
    0.07
    覧
    0.06
    ～↵↵
    0.06
     riots
    0.06
    .uml
    0.06
    ^^
    0.06
    ting
    0.06
    -wsj
    0.06
    -content
    0.06
    Act Density 0.016%

    No Known Activations