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

    Neuronpedia

    INDEX
    Explanations

    other websites/articles references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ue
    -0.07
     vyj
    -0.07
    iage
    -0.06
    邪
    -0.06
     inch
    -0.06
     bas
    -0.06
    -bel
    -0.06
    _z
    -0.06
    UED
    -0.06
     catalogue
    -0.06
    POSITIVE LOGITS
    -trash
    0.07
    FLOW
    0.06
     Consequently
    0.06
     Hampton
    0.06
     Palestin
    0.06
     lamps
    0.06
    τουργ
    0.06
     پوست
    0.06
    placeholders
    0.06
    .Mail
    0.06
    Act Density 0.007%

    No Known Activations