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

    Neuronpedia

    INDEX
    Explanations

    understanding mechanisms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    xcscheme
    0.42
     cheques
    0.39
     ставки
    0.38
     ставка
    0.38
     Awareness
    0.37
    你需要
    0.37
    所示
    0.36
    েনা
    0.36
    ラックス
    0.36
     estimado
    0.36
    POSITIVE LOGITS
     mechanisms
    1.11
     mechanism
    0.98
     Mechanisms
    0.95
    mechanism
    0.94
     mécanismes
    0.93
    Mechanism
    0.90
    mechan
    0.89
     dynamics
    0.88
     mecanismo
    0.86
    why
    0.84
    Act Density 0.021%

    No Known Activations