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

    Neuronpedia

    INDEX
    Explanations

    errors/mistakes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    components
    -0.07
    builders
    -0.07
    trainer
    -0.07
    _Mod
    -0.07
    	Array
    -0.06
    _completion
    -0.06
     cars
    -0.06
    “.
    -0.06
    нимает
    -0.06
    "But
    -0.06
    POSITIVE LOGITS
    .assertAlmostEqual
    0.07
    ousands
    0.06
    erdem
    0.06
    tparam
    0.06
     entertain
    0.06
    .Ge
    0.06
    ToDate
    0.06
     assort
    0.06
     응
    0.06
     teased
    0.06
    Act Density 0.011%

    No Known Activations