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

    Neuronpedia

    INDEX
    Explanations

    within

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Satan
    1.24
     Geç
    1.17
    けど
    1.16
     B
    1.14
     emotes
    1.13
     Disse
    1.12
     smelting
    1.11
    ki
    1.09
     methotrexate
    1.08
    }=\
    1.07
    POSITIVE LOGITS
    Qaeda
    1.12
    ⸱
    1.12
    сну
    1.08
    ங்கிணை
    1.05
    𝒂
    1.01
    serializer
    1.00
    UIView
    0.98
    ა
    0.98
    ર
    0.98
    вание
    0.97
    Act Density 0.111%

    No Known Activations