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

    Neuronpedia

    INDEX
    Explanations

    nor

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <Expression
    -0.07
    年龄
    -0.06
    개
    -0.06
    mez
    -0.06
    ßen
    -0.06
    wcs
    -0.06
     を
    -0.06
    tablename
    -0.06
    .idea
    -0.06
    (tree
    -0.06
    POSITIVE LOGITS
    &D
    0.07
    .Dictionary
    0.07
    asn
    0.07
     خل
    0.07
     redo
    0.06
     prat
    0.06
    Outlet
    0.06
     SAL
    0.06
    -Co
    0.06
     INLINE
    0.06
    Act Density 0.000%

    No Known Activations