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

    Neuronpedia

    INDEX
    Explanations

    instructions for starting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     चेन
    0.65
    чила
    0.64
     Print
    0.61
     Clients
    0.60
     bas
    0.59
     CHAIN
    0.58
     print
    0.58
     clients
    0.57
    ա
    0.56
     vòng
    0.56
    POSITIVE LOGITS
    极
    0.70
    Reg
    0.68
     تحقی
    0.66
     паро
    0.66
     Reg
    0.64
     Reflex
    0.63
     રિ
    0.63
     setMessage
    0.63
    reg
    0.62
    Register
    0.62
    Act Density 0.137%

    No Known Activations