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

    Neuronpedia

    INDEX
    Explanations

    domains and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     LinearLayout
    0.43
    🚵
    0.41
     हुने
    0.40
     stewards
    0.39
     layar
    0.39
     estimators
    0.37
    كيد
    0.37
    第一個
    0.37
    ้องกัน
    0.37
    ,"@
    0.37
    POSITIVE LOGITS
    3
    0.55
    7
    0.48
    8
    0.48
    mathbf
    0.47
    2
    0.44
    EDE
    0.43
    AR
    0.43
    ED
    0.41
    6
    0.41
    AY
    0.40
    Act Density 0.000%

    No Known Activations