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

    Neuronpedia

    INDEX
    Explanations

    final message

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Panic
    0.41
    Panic
    0.40
    getTargetContext
    0.40
    ।"
    0.39
     organismes
    0.39
    ི་
    0.39
    م
    0.39
    ұ
    0.38
    ப்பிரிக்க
    0.38
    тельностью
    0.38
    POSITIVE LOGITS
     activates
    0.53
     increases
    0.50
     activations
    0.49
     easiest
    0.49
     enhances
    0.45
     service
    0.44
     quarterfinals
    0.44
     annual
    0.43
     practices
    0.43
     represents
    0.42
    Act Density 0.006%

    No Known Activations