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

    Neuronpedia

    INDEX
    Explanations

    code/technical documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ########.
    -0.57
    NUMX
    -0.55
    publicain
    -0.52
    ganet
    -0.49
    kover
    -0.49
    朗
    -0.49
    Com
    -0.49
    vatore
    -0.47
    packt
    -0.47
    stands
    -0.47
    POSITIVE LOGITS
    TestingModule
    0.63
    AccessorTable
    0.59
    PyTuple
    0.56
    GraphicsUnit
    0.54
    ftagPool
    0.52
    transQ
    0.51
     Marlon
    0.51
    ActionCreators
    0.51
     griega
    0.50
    educated
    0.50
    Act Density 0.000%

    No Known Activations