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

    Neuronpedia

    INDEX
    Explanations

    propagation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mínimo
    -0.06
    :';↵
    -0.06
    383
    -0.06
    .accounts
    -0.06
    :',
    -0.06
     reconstruction
    -0.06
    殿
    -0.06
    agonal
    -0.06
    questions
    -0.06
     Costs
    -0.06
    POSITIVE LOGITS
     propagate
    0.08
    .setAlignment
    0.07
    igrated
    0.07
     immigr
    0.07
    {})
    0.07
     Dep
    0.07
    LOGGER
    0.07
    زارش
    0.07
     Anthrop
    0.07
    ")),
    0.07
    Act Density 0.003%

    No Known Activations