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

    Neuronpedia

    INDEX
    Explanations

    reduce air travel or vehicle use

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     வேலை
    0.39
    働き
    0.38
     процентов
    0.37
    槇
    0.37
    <tbody>
    0.36
     बि
    0.35
     dismantle
    0.34
    ESSAGE
    0.33
    ໑
    0.33
    骗
    0.33
    POSITIVE LOGITS
     Sum
    0.43
    icides
    0.42
    ificador
    0.42
     haha
    0.40
     enters
    0.39
    Sum
    0.38
    소서
    0.38
     lol
    0.38
     Somalia
    0.37
     Haha
    0.37
    Act Density 0.000%

    No Known Activations