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

    Neuronpedia

    INDEX
    Explanations

    Instructions or explanations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pars
    -0.07
    顿
    -0.06
    imachinery
    -0.06
    .bus
    -0.06
    _set
    -0.06
    .ant
    -0.06
     orb
    -0.06
     ус
    -0.06
    ��
    -0.06
     Sav
    -0.06
    POSITIVE LOGITS
    251
    0.07
    756
    0.06
     progression
    0.06
    ję
    0.06
    Also
    0.06
    )+'
    0.06
    ерап
    0.06
    olean
    0.06
    jets
    0.06
     Moroccan
    0.06
    Act Density 0.017%

    No Known Activations