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

    Neuronpedia

    INDEX
    Explanations

    geographical locations and programming languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused260>
    0.53
     ಕ್ರ
    0.49
    龴
    0.48
    vrdr
    0.47
    ཋ
    0.47
    𝗱
    0.47
    ма
    0.47
    า
    0.46
     ಅಮ
    0.45
    檤
    0.45
    POSITIVE LOGITS
     side
    0.49
     Embassy
    0.48
     Company
    0.47
     outpost
    0.46
    那边
    0.46
     trip
    0.46
     counterpart
    0.45
     embassy
    0.45
     India
    0.45
     y
    0.44
    Act Density 0.185%

    No Known Activations