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

    Neuronpedia

    INDEX
    Explanations

    family

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     courageous
    -0.07
     путем
    -0.06
     Assembly
    -0.06
     frustrating
    -0.06
     누구
    -0.06
     "_"
    -0.06
    HasBeen
    -0.06
     convicted
    -0.06
    _department
    -0.06
    :$
    -0.06
    POSITIVE LOGITS
     Sil
    0.07
    .';↵
    0.06
     reels
    0.06
    .sheet
    0.06
    UK
    0.06
    .Ag
    0.06
     sil
    0.06
    .NotNil
    0.06
    �ng
    0.06
    /random
    0.06
    Act Density 0.084%

    No Known Activations