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

    Neuronpedia

    INDEX
    Explanations

    RULE

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    вы
    -0.07
    ewing
    -0.07
     quella
    -0.07
     все
    -0.06
     polygons
    -0.06
    üm
    -0.06
     fundamental
    -0.06
    طف
    -0.06
    ậm
    -0.06
    惶
    -0.06
    POSITIVE LOGITS
    Pass
    0.07
    家居
    0.07
    -cert
    0.07
    震荡
    0.07
     STRING
    0.07
     incre
    0.07
    备考
    0.06
    terminated
    0.06
    县域
    0.06
    Teen
    0.06
    Act Density 0.001%

    No Known Activations