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

    Neuronpedia

    INDEX
    Explanations

    centrifuge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Russo
    -0.09
    Bak
    -0.08
     estrict
    -0.08
    .build
    -0.07
    Touched
    -0.07
     sanar
    -0.07
    建筑
    -0.07
     Prez
    -0.07
    straight
    -0.07
    .from
    -0.07
    POSITIVE LOGITS
     centrif
    0.10
    ണക്ക
    0.09
     Jeans
    0.08
     flotation
    0.08
     Geschwindigkeit
    0.08
     vitesse
    0.08
     крови
    0.08
     drums
    0.07
     panne
    0.07
     towering
    0.07
    Act Density 0.003%

    No Known Activations