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

    Neuronpedia

    INDEX
    Explanations

    past professional experience

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    新款
    0.29
     ফোন
    0.27
     durumda
    0.26
     പുതിയ
    0.26
     urination
    0.26
     moistened
    0.26
     સફેદ
    0.26
     disinfecting
    0.25
     manière
    0.25
     needles
    0.25
    POSITIVE LOGITS
    served
    0.34
     yılları
    0.33
     zunächst
    0.32
     successivement
    0.32
     работал
    0.32
     experiencia
    0.31
     Undergraduate
    0.31
    Served
    0.30
     сначала
    0.29
     served
    0.29
    Act Density 0.044%

    No Known Activations