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

    Neuronpedia

    INDEX
    Explanations

    security keys and exceptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    getContext
    0.42
    build
    0.40
     Nazar
    0.40
     justification
    0.39
    Yes
    0.36
    कभी
    0.36
    Feder
    0.36
     Bazar
    0.36
    CRE
    0.36
    generate
    0.36
    POSITIVE LOGITS
    fdata
    0.44
     akik
    0.43
    ව
    0.42
     bedside
    0.41
     pi
    0.41
     cita
    0.41
    ľa
    0.41
     dressings
    0.40
     opl
    0.40
     ci
    0.40
    Act Density 0.001%

    No Known Activations