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

    Neuronpedia

    INDEX
    Explanations

    words relating to countries and regions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     delineate
    0.50
     хирур
    0.49
     Req
    0.48
     pseud
    0.48
     სამ
    0.48
     bed
    0.47
     பால
    0.46
     тяжё
    0.46
     тяже
    0.45
     delim
    0.45
    POSITIVE LOGITS
    L
    0.66
     la
    0.57
    K
    0.55
    France
    0.50
    R
    0.50
    el
    0.49
    M
    0.48
    S
    0.45
    W
    0.45
    Fue
    0.45
    Act Density 0.000%

    No Known Activations