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

    Neuronpedia

    INDEX
    Explanations

    complex conditions and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     frug
    0.41
     scrimmage
    0.40
     midrange
    0.38
     terc
    0.38
     datetime
    0.38
     incompatibility
    0.37
     dollars
    0.37
     Readiness
    0.37
     same
    0.36
     matchups
    0.36
    POSITIVE LOGITS
    detailed
    0.42
     подробно
    0.42
    Kep
    0.40
     помимо
    0.40
    hee
    0.40
    quy
    0.39
     selain
    0.39
     भरपूर
    0.38
    menin
    0.38
    besides
    0.38
    Act Density 0.000%

    No Known Activations