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

    Neuronpedia

    INDEX
    Explanations

    work

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     coupling
    0.40
    strategy
    0.39
    ৃষ্ট
    0.38
     борьбы
    0.37
     খুব
    0.37
    营
    0.36
     реаги
    0.36
    araf
    0.36
     सुद्धा
    0.36
    🍕
    0.36
    POSITIVE LOGITS
     Arbeit
    0.40
     Undo
    0.40
    gebnisse
    0.39
    irus
    0.37
    лежа
    0.37
    hasFocus
    0.37
    acier
    0.37
     Transparency
    0.37
    ']*
    0.37
     Beschäft
    0.36
    Act Density 0.008%

    No Known Activations