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

    Neuronpedia

    INDEX
    Explanations

    weighted sum

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     antiquity
    0.41
     approfond
    0.41
    专业
    0.40
    Integral
    0.40
     पेशेवर
    0.40
    ष्टमी
    0.39
     Antiqu
    0.39
     सेठ
    0.39
     adolescence
    0.38
    房地产
    0.38
    POSITIVE LOGITS
    pond
    0.66
     ponder
    0.61
     pond
    0.54
     cuales
    0.52
     Pond
    0.51
    ponder
    0.49
     pondered
    0.47
     homot
    0.42
     ponds
    0.42
     geometrically
    0.42
    Act Density 0.023%

    No Known Activations