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

    Neuronpedia

    INDEX
    Explanations

    Ancient wars/battles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Immutable
    -0.08
     angekommen
    -0.08
    ображ
    -0.08
     imprim
    -0.08
     asfalt
    -0.08
     gambar
    -0.08
     Aplic
    -0.08
     provenance
    -0.07
     arrivé
    -0.07
     допуска
    -0.07
    POSITIVE LOGITS
     uprising
    0.11
     rebellion
    0.11
     rebels
    0.10
     confrontation
    0.10
    _attack
    0.09
     revolt
    0.09
     blockade
    0.09
     retaliation
    0.09
     বিরুদ্ধে
    0.09
    阻
    0.09
    Act Density 0.010%

    No Known Activations