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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     alo
    -0.07
    리에
    -0.07
    likes
    -0.06
    因
    -0.06
     �
    -0.06
    ahlen
    -0.06
    XXXXXXXX
    -0.06
    нице
    -0.06
     لي
    -0.06
    งเศ
    -0.06
    POSITIVE LOGITS
     skim
    0.06
    hread
    0.06
    MULT
    0.06
     kiss
    0.06
     debts
    0.06
    []=
    0.06
     showDialog
    0.06
    SBATCH
    0.06
    FML
    0.06
     pys
    0.06
    Act Density 0.000%

    No Known Activations