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

    Neuronpedia

    INDEX
    Explanations

    keywords followed by definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    as
    0.57
    users
    0.57
    short
    0.57
    inser
    0.57
    send
    0.57
    add
    0.57
    ise
    0.55
    user
    0.54
    cities
    0.54
    op
    0.53
    POSITIVE LOGITS
    муля
    0.51
     hoofd
    0.51
     figured
    0.51
     zaken
    0.50
     deporte
    0.48
     kaas
    0.48
     Gron
    0.47
     NY
    0.46
     phys
    0.46
     ambigu
    0.46
    Act Density 0.002%

    No Known Activations