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

    Neuronpedia

    INDEX
    Explanations

    new high-tech methods

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Laboratories
    -0.07
     spite
    -0.07
     Why
    -0.06
    вается
    -0.06
    "L
    -0.06
    しています
    -0.06
    ляется
    -0.06
     comfortably
    -0.06
    _cate
    -0.06
    Why
    -0.06
    POSITIVE LOGITS
    .getProperty
    0.07
     traverse
    0.07
    .hadoop
    0.06
    ureka
    0.06
     meta
    0.06
    xfe
    0.06
     hon
    0.06
     Employee
    0.06
    .getActive
    0.06
    PLOY
    0.06
    Act Density 0.075%

    No Known Activations