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

    Neuronpedia

    INDEX
    Explanations

    Code, programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tamp
    -0.07
    ut
    -0.07
    ymology
    -0.07
     diplomats
    -0.06
     Scandinavian
    -0.06
    .ut
    -0.06
    trait
    -0.06
     phần
    -0.06
    .us
    -0.06
     dedicate
    -0.06
    POSITIVE LOGITS
    ================
    0.09
     sinh
    0.07
     "==
    0.07
     XR
    0.07
     travelers
    0.06
    -fixed
    0.06
    (env
    0.06
    obili
    0.06
    _mC
    0.06
    ".↵
    0.06
    Act Density 0.000%

    No Known Activations