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

    Neuronpedia

    INDEX
    Explanations

    alternatives or choices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aisen
    0.33
    brasil
    0.31
    obre
    0.31
    yst
    0.30
    amer
    0.30
    alloc
    0.30
    reload
    0.30
    america
    0.30
    cid
    0.30
    ponen
    0.30
    POSITIVE LOGITS
     অথবা
    0.52
     কিংবা
    0.49
     или
    0.48
    あるいは
    0.46
     hoặc
    0.45
     अथवा
    0.45
     혹은
    0.45
     ወይም
    0.44
     或者
    0.44
     లేదా
    0.43
    Act Density 0.000%

    No Known Activations