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

    Neuronpedia

    INDEX
    Explanations

    eventual outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     აქვს
    0.64
     altid
    0.60
     olabilir
    0.58
     esteja
    0.57
    你是
    0.57
     generell
    0.57
    可能です
    0.56
     możesz
    0.55
     imati
    0.55
     memiliki
    0.55
    POSITIVE LOGITS
     вскоре
    1.49
     Subsequently
    1.45
    Then
    1.44
    その後
    1.39
     Then
    1.36
    Subsequently
    1.35
     then
    1.33
     Eventually
    1.32
     Thereafter
    1.32
    Soon
    1.30
    Act Density 0.283%

    No Known Activations