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

    Neuronpedia

    INDEX
    Explanations

    Adam, Adamant, Amara

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ނީ
    0.41
     मस्
    0.39
    }}$-
    0.38
    ಗಾರ
    0.38
    ﾚ
    0.38
    鸨
    0.37
    হান
    0.37
    respArray
    0.37
    PON
    0.37
    LIBRARY
    0.36
    POSITIVE LOGITS
     August
    0.39
    کان
    0.39
     Pers
    0.38
    ว
    0.38
     Europa
    0.38
    antine
    0.37
    íng
    0.37
     File
    0.37
     cardinality
    0.36
     Job
    0.35
    Act Density 0.004%

    No Known Activations