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

    Neuronpedia

    INDEX
    Explanations

    code special characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     achievement
    -0.08
    Dog
    -0.07
    -character
    -0.07
    ORE
    -0.07
     attività
    -0.07
    🤝
    -0.07
    Film
    -0.07
    FG
    -0.07
    ODY
    -0.06
     Humanity
    -0.06
    POSITIVE LOGITS
    บาคาร
    0.07
    .Back
    0.07
     scratched
    0.07
    ↛
    0.07
    protocol
    0.07
     оста
    0.07
    Normally
    0.07
     Nevertheless
    0.07
     gebru
    0.07
    ますが
    0.07
    Act Density 0.001%

    No Known Activations