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

    Neuronpedia

    INDEX
    Explanations

    logo

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    孝
    -0.07
     práce
    -0.06
     wonders
    -0.06
     Inch
    -0.06
    .")
↵
    -0.06
    embali
    -0.06
     Parkinson
    -0.06
    .mu
    -0.06
    ience
    -0.06
     лишь
    -0.06
    POSITIVE LOGITS
     inventions
    0.07
     tighten
    0.07
    śli
    0.07
    ostringstream
    0.07
     очеред
    0.07
    ật
    0.06
     odp
    0.06
     Mori
    0.06
    �
    0.06
    ，还
    0.06
    Act Density 0.014%

    No Known Activations