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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and connectors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    或其他
    0.21
     ($\
    0.21
    ."
    0.21
     अथवा
    0.21
    ，
    0.21
    ፣
    0.20
     ('
    0.20
     zurück
    0.20
    ាទ
    0.20
    、
    0.20
    POSITIVE LOGITS
     soprattutto
    0.28
     especially
    0.27
     क्योंकि
    0.27
     więc
    0.27
     though
    0.27
    क्योंकि
    0.26
    因为
    0.25
     although
    0.25
    although
    0.25
     pues
    0.25
    Act Density 0.926%

    No Known Activations