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

    Neuronpedia

    INDEX
    Explanations

    Police calls and federal agents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ersham
    0.41
    ederal
    0.41
     Plymouth
    0.40
     shilling
    0.38
    슘
    0.38
    깆
    0.36
    şiv
    0.36
    款
    0.36
     റെ
    0.36
    agamanam
    0.35
    POSITIVE LOGITS
     Strike
    0.61
     SES
    0.50
    Strike
    0.47
     strike
    0.46
     Task
    0.45
     vision
    0.43
    Task
    0.42
     توجه
    0.42
     remon
    0.40
     alleged
    0.40
    Act Density 0.002%

    No Known Activations