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

    Neuronpedia

    INDEX
    Explanations

    communication disadvantages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sencilla
    -0.09
    르면
    -0.09
     pursuits
    -0.08
     vegetar
    -0.08
     jakt
    -0.08
     relentlessly
    -0.08
     Superstar
    -0.08
     proceeded
    -0.08
     pursuit
    -0.08
     geführt
    -0.08
    POSITIVE LOGITS
     firsthand
    0.09
     interactive
    0.09
    直接
    0.08
     सीधे
    0.08
     direttamente
    0.08
     necessary
    0.08
     diretamente
    0.08
     lost
    0.08
     direto
    0.08
     معرض
    0.08
    Act Density 0.090%

    No Known Activations