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

    Neuronpedia

    INDEX
    Explanations

    say "of"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Powder
    -0.08
     indifference
    -0.07
    <Member
    -0.07
    MSG
    -0.07
     STOCK
    -0.07
     Bride
    -0.07
    #ad
    -0.07
    ombine
    -0.07
     supra
    -0.07
    _EST
    -0.07
    POSITIVE LOGITS
     quality
    0.08
    特朗
    0.07
    妘
    0.07
    짓
    0.07
     yürüt
    0.07
    ite
    0.07
    hm
    0.07
    젋
    0.07
    yan
    0.07
    epsilon
    0.07
    Act Density 0.119%

    No Known Activations