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

    Neuronpedia

    INDEX
    Explanations

    supply chain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     contentView
    0.45
     primos
    0.40
     Phi
    0.39
    之为
    0.37
     degenerate
    0.37
    仪
    0.37
    境界
    0.37
     inwon
    0.37
     Mira
    0.36
     Pele
    0.36
    POSITIVE LOGITS
     chain
    1.82
     chains
    1.58
     Chain
    1.55
    chain
    1.54
    Chain
    1.48
     CHAIN
    1.45
    链
    1.36
    鏈
    1.33
    チェーン
    1.32
     Chains
    1.30
    Act Density 0.017%

    No Known Activations