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

    Neuronpedia

    INDEX
    Explanations

    Syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    กรรมการ
    -0.07
    EventType
    -0.06
    urgence
    -0.06
    dados
    -0.06
    ql
    -0.06
    andles
    -0.06
     Protected
    -0.06
    riterion
    -0.06
     Indo
    -0.06
     organizace
    -0.06
    POSITIVE LOGITS
     lifelong
    0.07
    fixed
    0.07
     nær
    0.06
    PEAR
    0.06
     Tiny
    0.06
     tc
    0.06
     comprehensive
    0.06
    Ham
    0.06
    -context
    0.06
     CMP
    0.06
    Act Density 0.003%

    No Known Activations