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

    Neuronpedia

    INDEX
    Explanations

    simplification

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     सीसीटीवी
    0.52
    യ്യ
    0.46
    apay
    0.45
    GreaterThan
    0.45
    }>\
    0.44
    普通
    0.44
    ADOC
    0.44
     சக
    0.44
    Better
    0.43
    ゆっくり
    0.43
    POSITIVE LOGITS
     simplified
    2.64
     simplification
    2.58
     simplify
    2.47
     simplifying
    2.44
    简化
    2.31
     streamlined
    2.30
     simpl
    2.27
     shortened
    2.25
     Simplified
    2.25
     simplifies
    2.23
    Act Density 1.353%

    No Known Activations