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

    Neuronpedia

    INDEX
    Explanations

    automation, pharmaceutical, culture, cyber, Transformer, folklore, training, shopping, advertising

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     你
    0.88
     Thousands
    0.82
     thousands
    0.81
    Our
    0.80
     hundreds
    0.78
     dozens
    0.78
    thousands
    0.77
    !
    0.77
    夏天
    0.77
     centaines
    0.76
    POSITIVE LOGITS
     managerial
    1.07
     sociocultural
    0.96
    であるが
    0.96
    においても
    0.96
    においては
    0.96
    における
    0.95
     এরূপ
    0.94
    を用いる
    0.93
    に係る
    0.92
     interpersonal
    0.91
    Act Density 0.194%

    No Known Activations