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

    Neuronpedia

    INDEX
    Explanations

    two or more

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    मुना
    0.26
     pouvoirs
    0.26
    役割
    0.26
    ینګ
    0.26
     rayons
    0.26
     másik
    0.26
    像
    0.26
     حيات
    0.26
    Reservation
    0.25
    Zespół
    0.25
    POSITIVE LOGITS
    adoc
    0.30
    uo
    0.30
    ‚
    0.28
    ol
    0.26
    itable
    0.26
    uar
    0.25
    oa
    0.25
    ă
    0.25
    u
    0.25
     stated
    0.25
    Act Density 0.884%

    No Known Activations