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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _PA
    -0.07
    ンピ
    -0.06
    .trigger
    -0.06
    -exec
    -0.06
    remium
    -0.06
     administr
    -0.06
    bí
    -0.06
    uos
    -0.06
    -products
    -0.06
     recurrent
    -0.06
    POSITIVE LOGITS
     that
    0.08
     denen
    0.08
    that
    0.08
     THAT
    0.07
    That
    0.07
     dass
    0.07
     calidad
    0.07
     quella
    0.07
     bringen
    0.07
    	that
    0.07
    Act Density 0.063%

    No Known Activations