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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ماری
    -0.06
     lineage
    -0.06
     fleeing
    -0.06
    AAF
    -0.06
    Bullet
    -0.06
    ेव
    -0.05
    ники
    -0.05
    icions
    -0.05
    Task
    -0.05
    δοση
    -0.05
    POSITIVE LOGITS
     خواست
    0.07
     APPRO
    0.07
     내
    0.07
    ()]);↵
    0.06
     congressman
    0.06
     Sơn
    0.06
     Menu
    0.06
    円
    0.06
     Documentation
    0.06
    目前
    0.06
    Act Density 0.002%

    No Known Activations