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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hur
    -0.06
     elsif
    -0.06
    .Tx
    -0.06
     toggle
    -0.06
    ảo
    -0.06
     Eck
    -0.06
    ocide
    -0.06
    zzo
    -0.06
     beacon
    -0.06
    ्ध
    -0.06
    POSITIVE LOGITS
     труб
    0.07
     jealous
    0.06
    凡
    0.06
     vergi
    0.06
     enerj
    0.06
    99
    0.06
    -addons
    0.06
     Β
    0.06
    lanmıştır
    0.06
    斷
    0.06
    Act Density 0.031%

    No Known Activations