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

    Neuronpedia

    INDEX
    Explanations

    accordance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     міль
    -0.07
     citiz
    -0.07
    -0.06
    subtotal
    -0.06
     debtor
    -0.06
     người
    -0.06
    Smarty
    -0.06
     jew
    -0.06
     student
    -0.06
     Stap
    -0.06
    POSITIVE LOGITS
     accordance
    0.13
    การใช
    0.08
    ACH
    0.08
    Based
    0.08
    чить
    0.07
     Operating
    0.07
     Based
    0.07
     dealings
    0.07
    _race
    0.07
    ौद
    0.07
    Act Density 0.005%

    No Known Activations