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

    Neuronpedia

    INDEX
    Explanations

    macro vs common name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     van
    0.38
     Bath
    0.38
     суще
    0.38
     Cambridge
    0.38
     CSC
    0.37
     exced
    0.36
    Š
    0.36
     Communications
    0.36
     Совет
    0.36
     Combien
    0.35
    POSITIVE LOGITS
     disqualified
    0.41
    ้ม
    0.41
    λλην
    0.40
     unruly
    0.39
     orbiting
    0.38
     straighten
    0.38
     defiant
    0.38
    stung
    0.38
    taxonomy
    0.38
    籍
    0.38
    Act Density 0.000%

    No Known Activations