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

    Neuronpedia

    INDEX
    Explanations

    assistant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    the
    0.59
    britann
    0.57
    ﺕ
    0.56
    laboratory
    0.55
    thorax
    0.53
    faceted
    0.52
    JDK
    0.51
    timeout
    0.51
    dach
    0.49
    taste
    0.49
    POSITIVE LOGITS
    و
    0.55
    ية
    0.53
     zwar
    0.51
    يات
    0.50
    ето
    0.49
    его
    0.49
    ц
    0.48
    ু
    0.48
    е
    0.47
    ंगाबाद
    0.46
    Act Density 0.016%

    No Known Activations