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

    Neuronpedia

    INDEX
    Explanations

    lists of providers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     military
    0.42
    pillars
    0.40
     pillars
    0.39
     adherents
    0.38
     Received
    0.38
     crus
    0.38
     guardians
    0.38
     ambassadors
    0.38
     evidences
    0.38
    면
    0.37
    POSITIVE LOGITS
     luckily
    0.40
     `>=`,
    0.39
    newItem
    0.39
    ナナ
    0.39
    стно
    0.38
     forgot
    0.38
    চিব
    0.38
    rosis
    0.37
     ‏
    0.37
    henius
    0.37
    Act Density 0.000%

    No Known Activations