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

    Neuronpedia

    INDEX
    Explanations

    human needs and desires

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    node
    0.42
     Node
    0.40
     جوړونکی
    0.40
    サーバー
    0.37
    instruction
    0.36
     opted
    0.36
     textual
    0.36
     XML
    0.35
    页面
    0.35
     चेयरमैन
    0.35
    POSITIVE LOGITS
     tanpa
    0.46
     и
    0.46
     ও
    0.45
     بشكل
    0.43
    വ
    0.43
     durante
    0.43
     व
    0.43
     senza
    0.43
     outweighs
    0.43
     без
    0.42
    Act Density 0.233%

    No Known Activations