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

    Neuronpedia

    INDEX
    Explanations

    secondhand smoke

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ے
    0.58
    z
    0.57
     keinginan
    0.57
    い
    0.56
    ים
    0.56
    anza
    0.55
    ань
    0.53
    単品
    0.53
    ം
    0.51
    os
    0.49
    POSITIVE LOGITS
    :
    0.61
    >
    0.58
    \
    0.57
    ه
    0.56
    Children
    0.55
     polych
    0.53
     определя
    0.53
     cover
    0.52
     furiously
    0.52
    <0xB0>
    0.50
    Act Density 0.000%

    No Known Activations