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

    Neuronpedia

    INDEX
    Explanations

    two components or parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    の方法
    0.44
    Examples
    0.43
    socketList
    0.42
     relatos
    0.40
     procedimentos
    0.39
     thème
    0.39
     способов
    0.38
     obice
    0.38
     iniciativas
    0.38
    unity
    0.37
    POSITIVE LOGITS
     components
    1.15
     elements
    0.97
     компонен
    0.94
     componentes
    0.93
    components
    0.87
     parameters
    0.86
     component
    0.84
     komponen
    0.84
     Components
    0.82
     ingredients
    0.81
    Act Density 0.020%

    No Known Activations