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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     liabilities
    -0.07
    Banner
    -0.07
    _objs
    -0.06
    ritos
    -0.06
    rops
    -0.06
     presumption
    -0.06
    _city
    -0.06
    .djangoproject
    -0.06
    -------↵
    -0.06
    .Axis
    -0.06
    POSITIVE LOGITS
    عم
    0.07
    Strict
    0.07
     erle
    0.07
     Св
    0.06
     Cho
    0.06
    MING
    0.06
     Hassan
    0.06
     shard
    0.06
     Trav
    0.06
     fsm
    0.06
    Act Density 0.018%

    No Known Activations