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

    Neuronpedia

    INDEX
    Explanations

    general topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     मास्टर
    0.50
     master
    0.50
     Master
    0.50
    Master
    0.49
    emaster
    0.47
    master
    0.46
     мастер
    0.46
    MASTER
    0.46
    getMaster
    0.45
     MASTER
    0.44
    POSITIVE LOGITS
     allegory
    0.43
     noma
    0.42
     algebra
    0.42
     Survive
    0.40
    Episodes
    0.40
     allergy
    0.39
     allusion
    0.39
     complete
    0.39
    鋆
    0.39
     nutrition
    0.39
    Act Density 0.000%

    No Known Activations