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

    Neuronpedia

    INDEX
    Explanations

    making decisions and choices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ősz
    0.67
    oue
    0.62
     স্বভাব
    0.60
    মুনা
    0.60
    PLICATION
    0.59
    ائنات
    0.59
    ittances
    0.59
     られ
    0.58
    ὺς
    0.57
    USES
    0.57
    POSITIVE LOGITS
     decision
    5.73
     decisions
    5.48
    decision
    5.21
     Decision
    5.20
    Decision
    5.15
     Decisions
    4.93
     decisiones
    4.72
     décisions
    4.65
     decisión
    4.60
    决策
    4.58
    Act Density 0.809%

    No Known Activations