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

    Neuronpedia

    INDEX
    Explanations

    while / variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    公司
    0.46
    )：
    0.45
    夎
    0.45
    कर
    0.45
    kuat
    0.44
    內
    0.44
     chiropractor
    0.44
    精密
    0.44
     projektu
    0.44
    家里
    0.43
    POSITIVE LOGITS
     cah
    0.47
     Act
    0.47
     declaring
    0.47
     S
    0.46
     historic
    0.46
     proclam
    0.46
     adjourned
    0.46
     cancellations
    0.45
     actuar
    0.45
     pasting
    0.45
    Act Density 0.004%

    No Known Activations