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

    Neuronpedia

    INDEX
    Explanations

    own decisions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ata
    -0.07
    _js
    -0.06
    _BT
    -0.06
     kims
    -0.06
    Rs
    -0.06
     SAL
    -0.06
    xbb
    -0.06
    facebook
    -0.06
    FFFFFF
    -0.06
    AuthToken
    -0.06
    POSITIVE LOGITS
     grandchildren
    0.07
    (retval
    0.07
    (tile
    0.06
    eton
    0.06
    (argv
    0.06
    .utils
    0.06
    (proj
    0.06
    /\
    0.06
    ा:
    0.06
     [$
    0.06
    Act Density 0.022%

    No Known Activations