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

    Neuronpedia

    INDEX
    Explanations

    dividing lines and circles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atorial
    -0.08
     tun
    -0.08
    ling
    -0.07
     समुदाय
    -0.07
    ickou
    -0.07
    .subscribe
    -0.07
    intu
    -0.07
     initials
    -0.07
    /*.
    -0.07
    geta
    -0.07
    POSITIVE LOGITS
     percor
    0.09
     cruise
    0.08
    岸
    0.08
     comprimento
    0.08
     cuer
    0.08
     לאורך
    0.08
     luglio
    0.08
     beaches
    0.08
    跨度
    0.08
     кра
    0.08
    Act Density 0.005%

    No Known Activations