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

    Neuronpedia

    INDEX
    Explanations

    at the end

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     repatri
    0.41
     ดัง
    0.38
     conceivably
    0.38
    ivably
    0.37
    UIC
    0.37
     następ
    0.37
     sidel
    0.36
     TIC
    0.36
     Shoulder
    0.35
    semantic
    0.35
    POSITIVE LOGITS
     после
    0.82
     after
    0.77
     بعد
    0.75
     після
    0.73
    after
    0.67
     AFTER
    0.67
    After
    0.66
    底部
    0.64
     depois
    0.64
     baada
    0.64
    Act Density 0.022%

    No Known Activations