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

    Neuronpedia

    INDEX
    Explanations

    military alliances

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     токс
    -0.09
     brew
    -0.09
     enzyme
    -0.08
     fertilizer
    -0.08
     readership
    -0.08
    /p
    -0.08
     бутыл
    -0.08
     enzym
    -0.08
     candy
    -0.08
     perfume
    -0.08
    POSITIVE LOGITS
     interoper
    0.12
     NATO
    0.11
     interoperability
    0.11
    合作
    0.10
     sharing
    0.10
     cooperate
    0.10
    共享
    0.10
     cooperation
    0.10
     coopération
    0.10
     allies
    0.09
    Act Density 0.026%

    No Known Activations