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

    Neuronpedia

    INDEX
    Explanations

    Instructions or recipes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     verts
    -0.06
     Navigate
    -0.06
     massages
    -0.06
     invasive
    -0.06
    .labels
    -0.06
    OURCE
    -0.06
    batch
    -0.06
    brand
    -0.06
    stoi
    -0.06
     QB
    -0.06
    POSITIVE LOGITS
    카지노
    0.07
    /pkg
    0.07
    _CIPHER
    0.06
     rog
    0.06
     Gri
    0.06
    ارس
    0.06
    secret
    0.06
     ré
    0.06
    ρεια
    0.06
    ва
    0.06
    Act Density 0.001%

    No Known Activations