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

    Neuronpedia

    INDEX
    Explanations

    test

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wors
    -0.07
    abay
    -0.07
    _life
    -0.07
    stub
    -0.06
    luck
    -0.06
    -bg
    -0.06
     �
    -0.06
    _business
    -0.06
     wellness
    -0.06
    _pes
    -0.06
    POSITIVE LOGITS
    EditingController
    0.07
     significa
    0.07
    .toggle
    0.07
    ivol
    0.07
    璘
    0.07
    tablename
    0.07
    殖民
    0.07
    超过
    0.07
    جل
    0.07
     долл
    0.07
    Act Density 0.004%

    No Known Activations