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

    Neuronpedia

    INDEX
    Explanations

    medical conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    على
    0.54
    е
    0.53
    й
    0.53
    Также
    0.51
    м
    0.50
     Please
    0.49
     Robotics
    0.49
     Difficulty
    0.48
     Lymph
    0.48
    От
    0.48
    POSITIVE LOGITS
     admir
    0.49
     있고
    0.47
     emeritus
    0.45
     capping
    0.45
     bagging
    0.44
     domestically
    0.43
     formu
    0.42
    klore
    0.42
     fenn
    0.42
     manifesting
    0.41
    Act Density 0.000%

    No Known Activations