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

    Neuronpedia

    INDEX
    Explanations

    cutting and charts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tuscany
    0.43
     noi
    0.42
     curtail
    0.41
    ')){
    0.40
    DMA
    0.39
    ットン
    0.39
     comune
    0.38
    டுத்து
    0.38
     diminutive
    0.38
    }}\\
    0.38
    POSITIVE LOGITS
    নিম্ন
    0.41
    捭
    0.41
     Cutting
    0.39
    opically
    0.39
     Inorganic
    0.39
    Cutting
    0.38
    OP
    0.38
    ре
    0.38
    ਾਈ
    0.38
     PIR
    0.38
    Act Density 0.001%

    No Known Activations