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

    Neuronpedia

    INDEX
    Explanations

    code, references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tested
    -0.07
    antasy
    -0.06
     Checked
    -0.06
     males
    -0.06
    στε
    -0.06
     '::
    -0.06
    eturn
    -0.06
    _instruction
    -0.06
    about
    -0.06
    /mm
    -0.06
    POSITIVE LOGITS
    ″E
    0.06
     بأن
    0.06
     antiqu
    0.06
    ertia
    0.06
     cạnh
    0.06
     fkk
    0.06
     благ
    0.06
     المتحدة
    0.06
     DateTime
    0.06
    :::::::::::::
    0.06
    Act Density 0.000%

    No Known Activations