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

    Neuronpedia

    INDEX
    Explanations

    strategy implementation and games

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    S
    0.48
    AA
    0.43
    щее
    0.42
    Cl
    0.40
    ings
    0.39
    কে
    0.38
    Betty
    0.38
    riff
    0.38
    るので
    0.38
     fairy
    0.38
    POSITIVE LOGITS
     estrategia
    0.73
     стратегия
    0.71
     strate
    0.69
     стратеги
    0.68
     страте
    0.68
     estratégia
    0.67
     strategia
    0.67
     estrategias
    0.66
     strategie
    0.66
     estratég
    0.65
    Act Density 0.009%

    No Known Activations