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

    Neuronpedia

    INDEX
    Explanations

    as services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     quote
    0.75
     blessed
    0.73
     glee
    0.72
     crosses
    0.70
     jeg
    0.70
     sleepy
    0.70
     picnics
    0.69
     concur
    0.68
     blessings
    0.66
     cycles
    0.65
    POSITIVE LOGITS
    크
    1.07
    avity
    0.98
     fech
    0.95
    쐞
    0.94
    zelfde
    0.92
    ัก
    0.89
    ные
    0.88
    eldorf
    0.88
    ypeł
    0.88
    רים
    0.87
    Act Density 0.000%

    No Known Activations