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

    Neuronpedia

    INDEX
    Explanations

    assuming or creates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     현재
    0.48
    slaught
    0.48
     ಈಗ
    0.45
     යා
    0.44
     civilization
    0.44
     gravité
    0.43
     کە
    0.42
    ኃ
    0.42
     ప్రస్తుతం
    0.42
     या
    0.42
    POSITIVE LOGITS
    0
    0.53
    2
    0.47
    );
    0.46
    5
    0.46
     ⭐
    0.44
    6
    0.43
     Macy
    0.43
    1
    0.43
    itelj
    0.42
    假设
    0.42
    Act Density 0.004%

    No Known Activations