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

    Neuronpedia

    INDEX
    Explanations

    rider

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prevail
    -0.08
    (SC
    -0.07
    变态
    -0.07
    }`}
    -0.07
    留下来
    -0.07
     Preconditions
    -0.07
     fair
    -0.07
     heures
    -0.07
     "[
    -0.07
    .unlock
    -0.07
    POSITIVE LOGITS
     반드
    0.07
     aiding
    0.07
    irt
    0.07
    idel
    0.07
     citizens
    0.07
     Wir
    0.07
    들도
    0.07
    ירת
    0.07
    чная
    0.07
    namese
    0.06
    Act Density 0.006%

    No Known Activations