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

    Neuronpedia

    INDEX
    Explanations

    caffeine withdrawal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tahmin
    0.41
    できます
    0.39
    បង្កើត
    0.39
     leptons
    0.39
     यकीन
    0.38
    がない
    0.38
     verke
    0.38
     leiden
    0.38
     নিশ্চিত
    0.38
     hydrothermal
    0.38
    POSITIVE LOGITS
     Curved
    0.38
     curved
    0.38
     विज
    0.37
    매
    0.36
     بای
    0.36
    льбе
    0.36
    చ్
    0.35
     puls
    0.35
     Roberto
    0.35
     loves
    0.35
    Act Density 0.006%

    No Known Activations