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

    Neuronpedia

    INDEX
    Explanations

    stronger

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     immunization
    0.43
    ointments
    0.38
    PN
    0.38
     oaths
    0.37
    ಪಟ್ಟ
    0.37
     royalties
    0.36
     វា
    0.36
    蘸
    0.36
    Rain
    0.35
     అవకాశ
    0.35
    POSITIVE LOGITS
    щими
    0.42
     বাসিন্দা
    0.41
     🥰
    0.37
     certain
    0.37
     stronger
    0.36
    大小
    0.35
    াতাড়ি
    0.35
     nowadays
    0.35
     invariably
    0.35
    select
    0.35
    Act Density 0.000%

    No Known Activations