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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "Our
    -0.09
    your
    -0.07
    Our
    -0.07
    my
    -0.07
     評
    -0.07
     Our
    -0.07
    _issues
    -0.07
     YOUR
    -0.06
    Pakistan
    -0.06
    èo
    -0.06
    POSITIVE LOGITS
     también
    0.07
     сид
    0.06
     yüz
    0.06
     trag
    0.06
    ELSE
    0.06
    _lower
    0.06
     annihil
    0.06
     اک
    0.06
    {_
    0.06
     scrutin
    0.06
    Act Density 0.100%

    No Known Activations