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

    Neuronpedia

    INDEX
    Explanations

    practices, tactics, and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Value
    0.53
     skillset
    0.49
    Time
    0.46
    প্রেস
    0.46
    Skill
    0.46
    6
    0.45
    Set
    0.45
    and
    0.44
    Process
    0.44
    Plan
    0.44
    POSITIVE LOGITS
     abuso
    0.55
     comportamenti
    0.55
     esclusivamente
    0.53
     ataques
    0.53
     fraudulently
    0.51
     indiscrimin
    0.51
     medicamentos
    0.50
     abus
    0.49
     gleichen
    0.48
     држа
    0.48
    Act Density 0.108%

    No Known Activations