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

    Neuronpedia

    INDEX
    Explanations

    say "size"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    services
    -0.08
     theology
    -0.07
     presumably
    -0.07
     bonds
    -0.07
     jails
    -0.07
     RETURNS
    -0.06
    ologies
    -0.06
    άς
    -0.06
     borrower
    -0.06
     BaseType
    -0.06
    POSITIVE LOGITS
    取得
    0.06
    em
    0.06
    yssey
    0.06
     när
    0.06
    튜
    0.06
    �
    0.06
     conseg
    0.06
    )+
    0.06
     इसम
    0.06
    	cuda
    0.06
    Act Density 0.058%

    No Known Activations