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

    Neuronpedia

    INDEX
    Explanations

    evolved and programmed responses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ENN
    0.40
    chips
    0.39
    Analysts
    0.39
    Stocks
    0.39
     округа
    0.38
    Sizes
    0.38
    Ring
    0.38
     RESON
    0.38
    inis
    0.38
    isco
    0.37
    POSITIVE LOGITS
     murderous
    0.47
     enfon
    0.45
     patrolling
    0.44
     dét
    0.42
     reconstru
    0.42
     combatir
    0.42
     Combat
    0.41
     embroiled
    0.41
     combat
    0.41
     avanç
    0.40
    Act Density 0.004%

    No Known Activations