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

    Neuronpedia

    INDEX
    Explanations

    have/has/had followed by past participle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    曾經
    0.23
     เคย
    0.22
    เคย
    0.20
     compensatory
    0.19
     יכול
    0.18
     zuvor
    0.18
     bazı
    0.18
     നേടി
    0.18
     hadde
    0.18
     previamente
    0.18
    POSITIVE LOGITS
     essentially
    0.24
     presented
    0.20
     aim
    0.19
     literally
    0.19
     ironically
    0.18
     basically
    0.18
     arguably
    0.18
     aimed
    0.18
     kept
    0.18
     largely
    0.18
    Act Density 0.080%

    No Known Activations