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

    Neuronpedia

    INDEX
    Explanations

    tech stack or ecosystem

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ब्लाइंड
    0.24
    敦煌
    0.23
     Exhib
    0.23
    bindParam
    0.23
     влади
    0.22
     préalable
    0.22
     Medellín
    0.22
    rines
    0.22
    ških
    0.22
    Ц
    0.22
    POSITIVE LOGITS
    ի
    0.27
    ittaa
    0.27
     wagons
    0.26
    ak
    0.25
    ownicy
    0.25
     scope
    0.24
     panic
    0.24
     작성
    0.24
    thias
    0.24
    kreis
    0.24
    Act Density 0.030%

    No Known Activations