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

    Neuronpedia

    INDEX
    Explanations

    Special characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     πρά
    -0.08
    Besides
    -0.07
     Besides
    -0.07
     Restart
    -0.07
    ihar
    -0.07
    Profit
    -0.06
    ैत
    -0.06
     rest
    -0.06
     Baptist
    -0.06
     Normally
    -0.06
    POSITIVE LOGITS
    куп
    0.07
    eldig
    0.06
    реди
    0.06
    間に
    0.06
     좋
    0.06
     случай
    0.06
    (contents
    0.06
    .ViewHolder
    0.06
     него
    0.06
     arada
    0.06
    Act Density 0.015%

    No Known Activations