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

    Neuronpedia

    INDEX
    Explanations

    author names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ouro
    -0.07
    byt
    -0.07
    _que
    -0.06
    AYS
    -0.06
    ้นท
    -0.06
    (plan
    -0.06
    Quiz
    -0.06
     таких
    -0.06
    ays
    -0.06
    uffman
    -0.06
    POSITIVE LOGITS
     культур
    0.06
     acknow
    0.06
     предус
    0.06
     नगर
    0.06
    (const
    0.06
     aconte
    0.06
     italian
    0.06
    ชนะ
    0.06
    -vis
    0.06
    	Schema
    0.06
    Act Density 0.024%

    No Known Activations