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

    Neuronpedia

    INDEX
    Explanations

    rule based systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    0.45
     propiet
    0.42
    ្វ
    0.42
    ش
    0.42
     stockbild
    0.41
     diren
    0.41
     санк
    0.40
    リック
    0.40
     plano
    0.40
    ิล
    0.40
    POSITIVE LOGITS
    Rules
    1.05
    rule
    1.04
     rule
    1.03
     rules
    1.02
    Rule
    0.98
    rules
    0.96
     Rules
    0.93
     Rule
    0.93
     규칙
    0.89
    规则
    0.89
    Act Density 0.007%

    No Known Activations